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 2020/08/05 11:10:56 UTC
[hive] branch master updated: HIVE-23937: Take null ordering into
consideration when pushing TNK through inner joins (Attila Magyar,
reviewed by Krisztian Kasa)
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 05bbaf4 HIVE-23937: Take null ordering into consideration when pushing TNK through inner joins (Attila Magyar, reviewed by Krisztian Kasa)
05bbaf4 is described below
commit 05bbaf452b92d13733bc5226666c83719aaba67d
Author: Attila Magyar <am...@hortonworks.com>
AuthorDate: Wed Aug 5 13:10:47 2020 +0200
HIVE-23937: Take null ordering into consideration when pushing TNK through inner joins (Attila Magyar, reviewed by Krisztian Kasa)
---
.../topnkey/TopNKeyPushdownProcessor.java | 85 ++---------
.../queries/clientpositive/topnkey_inner_join.q | 10 +-
.../queries/clientpositive/topnkey_inner_join2.q | 4 +-
.../clientpositive/llap/topnkey_inner_join.q.out | 162 ++++++++++----------
.../clientpositive/llap/topnkey_inner_join2.q.out | 36 ++---
.../perf/tez/constraints/mv_query44.q.out | 118 +++++++--------
.../perf/tez/constraints/query44.q.out | 118 +++++++--------
.../perf/tez/constraints/query65.q.out | 168 ++++++++++-----------
.../perf/tez/constraints/query99.q.out | 132 ++++++++--------
9 files changed, 387 insertions(+), 446 deletions(-)
diff --git a/ql/src/java/org/apache/hadoop/hive/ql/optimizer/topnkey/TopNKeyPushdownProcessor.java b/ql/src/java/org/apache/hadoop/hive/ql/optimizer/topnkey/TopNKeyPushdownProcessor.java
index 88c99c4..b8e5ba9 100644
--- a/ql/src/java/org/apache/hadoop/hive/ql/optimizer/topnkey/TopNKeyPushdownProcessor.java
+++ b/ql/src/java/org/apache/hadoop/hive/ql/optimizer/topnkey/TopNKeyPushdownProcessor.java
@@ -34,9 +34,7 @@ import org.apache.hadoop.hive.ql.lib.Node;
import org.apache.hadoop.hive.ql.lib.NodeProcessorCtx;
import org.apache.hadoop.hive.ql.lib.SemanticNodeProcessor;
import org.apache.hadoop.hive.ql.parse.SemanticException;
-import org.apache.hadoop.hive.ql.plan.ExprNodeColumnDesc;
import org.apache.hadoop.hive.ql.plan.ExprNodeDesc;
-import org.apache.hadoop.hive.ql.plan.ExprNodeDescUtils;
import org.apache.hadoop.hive.ql.plan.GroupByDesc;
import org.apache.hadoop.hive.ql.plan.JoinCondDesc;
import org.apache.hadoop.hive.ql.plan.JoinDesc;
@@ -278,87 +276,28 @@ public class TopNKeyPushdownProcessor implements SemanticNodeProcessor {
LOG.debug("Not pushing {} through {} as non FK side of the join is filtered", topNKey.getName(), join.getName());
return;
}
- // Check column origins:
- // 1. If all OrderBy columns are coming from the child (FK) table:
- // -> move TopNKeyOperator
- // 2. If the first n OrderBy columns are coming from the child (FK) table:
- // -> copy TopNKeyOperator with the first n columns, and leave the original in place
- int prefixLength = keyColumnPrefixLength(join, topNKey, fkJoinInputIndex, topNKey.getConf().getKeyColumns());
- if (prefixLength == 0) {
- LOG.debug("Not pushing {} through {} as common key column prefix length is 0", topNKey.getName(), join.getName());
+ CommonKeyPrefix commonKeyPrefix = CommonKeyPrefix.map(
+ mapUntilColumnEquals(topNKeyDesc.getKeyColumns(), join.getColumnExprMap()),
+ topNKeyDesc.getColumnSortOrder(),
+ topNKeyDesc.getNullOrder(),
+ fkJoinInput.getConf().getKeyCols(),
+ fkJoinInput.getConf().getColumnExprMap(),
+ fkJoinInput.getConf().getOrder(),
+ fkJoinInput.getConf().getNullOrder());
+ if (commonKeyPrefix.isEmpty() || commonKeyPrefix.size() == topNKeyDesc.getPartitionKeyColumns().size()) {
return;
}
LOG.debug("Pushing a copy of {} through {} and {}",
topNKey.getName(), join.getName(), fkJoinInput.getName());
- TopNKeyDesc newTopNKeyDesc = topNKeyDesc.withKeyColumns(prefixLength);
- newTopNKeyDesc.setKeyColumns(remapColumns(join, fkJoinInput, newTopNKeyDesc.getKeyColumns()));
+ final TopNKeyDesc newTopNKeyDesc = topNKeyDesc.combine(commonKeyPrefix);
pushdown(copyDown(fkJoinInput, newTopNKeyDesc));
- if (topNKeyDesc.getKeyColumns().size() == prefixLength) {
+
+ if (topNKeyDesc.getKeyColumns().size() == commonKeyPrefix.size()) {
LOG.debug("Removing {} above {}", topNKey.getName(), join.getName());
join.removeChildAndAdoptItsChildren(topNKey);
}
}
- /**
- * Check if the first n keyColumns of the TopNKeyFilter
- * are coming from expected side of the join (indicated by the expectedTag).
- * @return n
- */
- private int keyColumnPrefixLength(
- CommonJoinOperator<? extends JoinDesc> join,
- TopNKeyOperator topNKeyOperator,
- int expectedTag,
- List<ExprNodeDesc> keyColumns) {
- int commonPrefixLength = 0;
- for (ExprNodeDesc orderByKey : keyColumns) {
- if (tag(join, topNKeyOperator, orderByKey) == expectedTag) {
- commonPrefixLength++;
- } else {
- return commonPrefixLength;
- }
- }
- return commonPrefixLength;
- }
-
- private int tag(CommonJoinOperator<? extends JoinDesc> join, TopNKeyOperator topNKeyOperator, ExprNodeDesc column) {
- String colName = columnOutputName(join, topNKeyOperator, column);
- if (colName == null) {
- return -1;
- }
- Byte tag = join.getConf().getReversedExprs().get(colName);
- return tag == null ? -1 : tag;
- }
-
- private String columnOutputName(CommonJoinOperator<? extends JoinDesc> join, TopNKeyOperator topNKeyOperator, ExprNodeDesc column) {
- ExprNodeDesc joinExprNode = backtrack(join, topNKeyOperator, column);
- if (joinExprNode == null) {
- return null;
- }
- for (Map.Entry<String, ExprNodeDesc> e : join.getColumnExprMap().entrySet()) {
- if (e.getValue() == joinExprNode) {
- return e.getKey();
- }
- }
- return null;
- }
-
- private ExprNodeDesc backtrack(CommonJoinOperator<? extends JoinDesc> join, TopNKeyOperator topNKeyOperator, ExprNodeDesc column) {
- try {
- ExprNodeDesc joinExprNode = ExprNodeDescUtils.backtrack(column, topNKeyOperator, join);
- if (joinExprNode == null || !(joinExprNode instanceof ExprNodeColumnDesc)) {
- return null;
- }
- return joinExprNode;
- } catch (SemanticException e) {
- throw new RuntimeException(e);
- }
- }
-
- private List<ExprNodeDesc> remapColumns(CommonJoinOperator<? extends JoinDesc> join, ReduceSinkOperator fkJoinInput, List<ExprNodeDesc> topNKeyColumns) {
- List<ExprNodeDesc> joinCols = mapColumns(topNKeyColumns, join.getColumnExprMap());
- return mapColumns(joinCols, fkJoinInput.getColumnExprMap());
- }
-
private List<ExprNodeDesc> mapUntilColumnEquals(List<ExprNodeDesc> columns, Map<String,
ExprNodeDesc> colExprMap) {
if (colExprMap == null) {
diff --git a/ql/src/test/queries/clientpositive/topnkey_inner_join.q b/ql/src/test/queries/clientpositive/topnkey_inner_join.q
index 81144f8..21c2bdf 100644
--- a/ql/src/test/queries/clientpositive/topnkey_inner_join.q
+++ b/ql/src/test/queries/clientpositive/topnkey_inner_join.q
@@ -25,10 +25,10 @@ set hive.optimize.topnkey=true;
set hive.optimize.limittranspose=false;
select 'positive: order by columns are coming from child table';
-explain select * from orders join customer on customer.id = orders.customer_id order by orders.amount limit 3;
+explain select * from orders join customer on customer.id = orders.customer_id order by orders.customer_id limit 3;
explain select * from orders join customer on customer.id = orders.customer_id order by orders.customer_id, orders.amount limit 3;
explain select * from customer join orders on orders.customer_id = customer.id order by orders.amount, orders.customer_id limit 3;
-select * from orders join customer on customer.id = orders.customer_id order by orders.amount limit 3;
+select * from orders join customer on customer.id = orders.customer_id order by orders.customer_id limit 3;
select * from orders join customer on customer.id = orders.customer_id order by orders.customer_id, orders.amount limit 3;
select * from customer join orders on orders.customer_id = customer.id order by orders.amount, orders.customer_id limit 3;
@@ -43,10 +43,10 @@ explain select * from orders join customer on customer.id = orders.customer_id o
select * from orders join customer on customer.id = orders.customer_id order by customer.name, orders.amount limit 3;
select 'mixed/positive: 1st n order by columns are coming from child table';
-explain select * from orders join customer on customer.id = orders.customer_id order by orders.amount, customer.name limit 3;
-select * from orders join customer on customer.id = orders.customer_id order by orders.amount, customer.name limit 3;
+explain select * from orders join customer on customer.id = orders.customer_id order by orders.customer_id, customer.name limit 3;
+select * from orders join customer on customer.id = orders.customer_id order by orders.customer_id, customer.name limit 3;
-select 'positive: nulls first';
+select 'negative: nulls first';
explain select * from customer join orders on orders.customer_id = customer.id order by customer_id nulls first limit 1;
select * from customer join orders on orders.customer_id = customer.id order by customer_id nulls first limit 1;
diff --git a/ql/src/test/queries/clientpositive/topnkey_inner_join2.q b/ql/src/test/queries/clientpositive/topnkey_inner_join2.q
index ce20f82..dcbc18f 100644
--- a/ql/src/test/queries/clientpositive/topnkey_inner_join2.q
+++ b/ql/src/test/queries/clientpositive/topnkey_inner_join2.q
@@ -45,12 +45,12 @@ explain select name, city
from customer join address
on customer.address_id = address.id
and name in ('Joe', 'Robert','Heisenberg')
- order by customer.id
+ order by customer.address_id
limit 3;
select name, city
from customer join address
on customer.address_id = address.id
and name in ('Joe', 'Robert','Heisenberg')
- order by customer.id
+ order by customer.address_id
limit 3;
diff --git a/ql/src/test/results/clientpositive/llap/topnkey_inner_join.q.out b/ql/src/test/results/clientpositive/llap/topnkey_inner_join.q.out
index 7719593..63580ee 100644
--- a/ql/src/test/results/clientpositive/llap/topnkey_inner_join.q.out
+++ b/ql/src/test/results/clientpositive/llap/topnkey_inner_join.q.out
@@ -80,12 +80,12 @@ POSTHOOK: type: QUERY
POSTHOOK: Input: _dummy_database@_dummy_table
#### A masked pattern was here ####
positive: order by columns are coming from child table
-PREHOOK: query: explain select * from orders join customer on customer.id = orders.customer_id order by orders.amount limit 3
+PREHOOK: query: explain select * from orders join customer on customer.id = orders.customer_id order by orders.customer_id limit 3
PREHOOK: type: QUERY
PREHOOK: Input: default@customer
PREHOOK: Input: default@orders
#### A masked pattern was here ####
-POSTHOOK: query: explain select * from orders join customer on customer.id = orders.customer_id order by orders.amount limit 3
+POSTHOOK: query: explain select * from orders join customer on customer.id = orders.customer_id order by orders.customer_id limit 3
POSTHOOK: type: QUERY
POSTHOOK: Input: default@customer
POSTHOOK: Input: default@orders
@@ -114,7 +114,7 @@ STAGE PLANS:
Statistics: Num rows: 5 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE
Top N Key Operator
sort order: +
- keys: amount (type: int)
+ keys: customer_id (type: int)
null sort order: z
Statistics: Num rows: 5 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE
top n: 3
@@ -161,16 +161,16 @@ STAGE PLANS:
outputColumnNames: _col0, _col1, _col2, _col3, _col4
Statistics: Num rows: 5 Data size: 1016 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
- key expressions: _col1 (type: int)
+ key expressions: _col0 (type: int)
null sort order: z
sort order: +
Statistics: Num rows: 5 Data size: 1016 Basic stats: COMPLETE Column stats: COMPLETE
- value expressions: _col0 (type: int), _col2 (type: int), _col3 (type: string), _col4 (type: string)
+ value expressions: _col1 (type: int), _col2 (type: int), _col3 (type: string), _col4 (type: string)
Reducer 3
Execution mode: vectorized, llap
Reduce Operator Tree:
Select Operator
- expressions: VALUE._col0 (type: int), KEY.reducesinkkey0 (type: int), VALUE._col1 (type: int), VALUE._col2 (type: string), VALUE._col3 (type: string)
+ expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: int), VALUE._col1 (type: int), VALUE._col2 (type: string), VALUE._col3 (type: string)
outputColumnNames: _col0, _col1, _col2, _col3, _col4
Statistics: Num rows: 5 Data size: 1016 Basic stats: COMPLETE Column stats: COMPLETE
Limit
@@ -223,9 +223,9 @@ STAGE PLANS:
predicate: customer_id is not null (type: boolean)
Statistics: Num rows: 5 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE
Top N Key Operator
- sort order: ++
- keys: customer_id (type: int), amount (type: int)
- null sort order: zz
+ sort order: +
+ keys: customer_id (type: int)
+ null sort order: z
Statistics: Num rows: 5 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE
top n: 3
Select Operator
@@ -270,25 +270,31 @@ STAGE PLANS:
1 _col0 (type: int)
outputColumnNames: _col0, _col1, _col2, _col3, _col4
Statistics: Num rows: 5 Data size: 1016 Basic stats: COMPLETE Column stats: COMPLETE
- Reduce Output Operator
- key expressions: _col0 (type: int), _col1 (type: int)
- null sort order: zz
+ Top N Key Operator
sort order: ++
+ keys: _col0 (type: int), _col1 (type: int)
+ null sort order: zz
Statistics: Num rows: 5 Data size: 1016 Basic stats: COMPLETE Column stats: COMPLETE
- value expressions: _col2 (type: int), _col3 (type: string), _col4 (type: string)
+ top n: 3
+ Reduce Output Operator
+ key expressions: _col0 (type: int), _col1 (type: int)
+ null sort order: zz
+ sort order: ++
+ Statistics: Num rows: 5 Data size: 1016 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col2 (type: int), _col3 (type: string), _col4 (type: string)
Reducer 3
Execution mode: vectorized, llap
Reduce Operator Tree:
Select Operator
expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: int), VALUE._col0 (type: int), VALUE._col1 (type: string), VALUE._col2 (type: string)
outputColumnNames: _col0, _col1, _col2, _col3, _col4
- Statistics: Num rows: 5 Data size: 1016 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 5 Data size: 1008 Basic stats: COMPLETE Column stats: COMPLETE
Limit
Number of rows: 3
- Statistics: Num rows: 3 Data size: 612 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 3 Data size: 608 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 3 Data size: 612 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 3 Data size: 608 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -350,23 +356,17 @@ STAGE PLANS:
Filter Operator
predicate: customer_id is not null (type: boolean)
Statistics: Num rows: 5 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE
- Top N Key Operator
- sort order: ++
- keys: amount (type: int), customer_id (type: int)
- null sort order: zz
+ Select Operator
+ expressions: customer_id (type: int), amount (type: int)
+ outputColumnNames: _col0, _col1
Statistics: Num rows: 5 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE
- top n: 3
- Select Operator
- expressions: customer_id (type: int), amount (type: int)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 5 Data size: 36 Basic stats: COMPLETE Column stats: COMPLETE
- Reduce Output Operator
- key expressions: _col0 (type: int)
- null sort order: z
- sort order: +
- Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 5 Data size: 36 Basic stats: COMPLETE Column stats: COMPLETE
- value expressions: _col1 (type: int)
+ Reduce Output Operator
+ key expressions: _col0 (type: int)
+ null sort order: z
+ sort order: +
+ Map-reduce partition columns: _col0 (type: int)
+ Statistics: Num rows: 5 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col1 (type: int)
Execution mode: vectorized, llap
LLAP IO: all inputs
Reducer 2
@@ -379,13 +379,19 @@ STAGE PLANS:
0 _col0 (type: int)
1 _col0 (type: int)
outputColumnNames: _col0, _col1, _col2, _col3, _col4
- Statistics: Num rows: 5 Data size: 1016 Basic stats: COMPLETE Column stats: COMPLETE
- Reduce Output Operator
- key expressions: _col4 (type: int), _col3 (type: int)
- null sort order: zz
+ Statistics: Num rows: 5 Data size: 1020 Basic stats: COMPLETE Column stats: COMPLETE
+ Top N Key Operator
sort order: ++
- Statistics: Num rows: 5 Data size: 1016 Basic stats: COMPLETE Column stats: COMPLETE
- value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string)
+ keys: _col4 (type: int), _col3 (type: int)
+ null sort order: zz
+ Statistics: Num rows: 5 Data size: 1020 Basic stats: COMPLETE Column stats: COMPLETE
+ top n: 3
+ Reduce Output Operator
+ key expressions: _col4 (type: int), _col3 (type: int)
+ null sort order: zz
+ sort order: ++
+ Statistics: Num rows: 5 Data size: 1020 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string)
Reducer 3
Execution mode: vectorized, llap
Reduce Operator Tree:
@@ -410,19 +416,19 @@ STAGE PLANS:
Processor Tree:
ListSink
-PREHOOK: query: select * from orders join customer on customer.id = orders.customer_id order by orders.amount limit 3
+PREHOOK: query: select * from orders join customer on customer.id = orders.customer_id order by orders.customer_id limit 3
PREHOOK: type: QUERY
PREHOOK: Input: default@customer
PREHOOK: Input: default@orders
#### A masked pattern was here ####
-POSTHOOK: query: select * from orders join customer on customer.id = orders.customer_id order by orders.amount limit 3
+POSTHOOK: query: select * from orders join customer on customer.id = orders.customer_id order by orders.customer_id limit 3
POSTHOOK: type: QUERY
POSTHOOK: Input: default@customer
POSTHOOK: Input: default@orders
#### A masked pattern was here ####
-3 30 3 Smith smith@email.com
-3 40 3 Smith smith@email.com
+1 100 1 Robinson robinson@email.com
1 50 1 Robinson robinson@email.com
+2 200 2 Jones jones@email.com
PREHOOK: query: select * from orders join customer on customer.id = orders.customer_id order by orders.customer_id, orders.amount limit 3
PREHOOK: type: QUERY
PREHOOK: Input: default@customer
@@ -845,12 +851,12 @@ POSTHOOK: type: QUERY
POSTHOOK: Input: _dummy_database@_dummy_table
#### A masked pattern was here ####
mixed/positive: 1st n order by columns are coming from child table
-PREHOOK: query: explain select * from orders join customer on customer.id = orders.customer_id order by orders.amount, customer.name limit 3
+PREHOOK: query: explain select * from orders join customer on customer.id = orders.customer_id order by orders.customer_id, customer.name limit 3
PREHOOK: type: QUERY
PREHOOK: Input: default@customer
PREHOOK: Input: default@orders
#### A masked pattern was here ####
-POSTHOOK: query: explain select * from orders join customer on customer.id = orders.customer_id order by orders.amount, customer.name limit 3
+POSTHOOK: query: explain select * from orders join customer on customer.id = orders.customer_id order by orders.customer_id, customer.name limit 3
POSTHOOK: type: QUERY
POSTHOOK: Input: default@customer
POSTHOOK: Input: default@orders
@@ -879,7 +885,7 @@ STAGE PLANS:
Statistics: Num rows: 5 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE
Top N Key Operator
sort order: +
- keys: amount (type: int)
+ keys: customer_id (type: int)
null sort order: z
Statistics: Num rows: 5 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE
top n: 3
@@ -927,21 +933,21 @@ STAGE PLANS:
Statistics: Num rows: 5 Data size: 1016 Basic stats: COMPLETE Column stats: COMPLETE
Top N Key Operator
sort order: ++
- keys: _col1 (type: int), _col3 (type: string)
+ keys: _col0 (type: int), _col3 (type: string)
null sort order: zz
Statistics: Num rows: 5 Data size: 1016 Basic stats: COMPLETE Column stats: COMPLETE
top n: 3
Reduce Output Operator
- key expressions: _col1 (type: int), _col3 (type: string)
+ key expressions: _col0 (type: int), _col3 (type: string)
null sort order: zz
sort order: ++
Statistics: Num rows: 5 Data size: 1016 Basic stats: COMPLETE Column stats: COMPLETE
- value expressions: _col0 (type: int), _col2 (type: int), _col4 (type: string)
+ value expressions: _col1 (type: int), _col2 (type: int), _col4 (type: string)
Reducer 3
Execution mode: vectorized, llap
Reduce Operator Tree:
Select Operator
- expressions: VALUE._col0 (type: int), KEY.reducesinkkey0 (type: int), VALUE._col1 (type: int), KEY.reducesinkkey1 (type: string), VALUE._col2 (type: string)
+ expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: int), VALUE._col1 (type: int), KEY.reducesinkkey1 (type: string), VALUE._col2 (type: string)
outputColumnNames: _col0, _col1, _col2, _col3, _col4
Statistics: Num rows: 5 Data size: 1008 Basic stats: COMPLETE Column stats: COMPLETE
Limit
@@ -961,28 +967,28 @@ STAGE PLANS:
Processor Tree:
ListSink
-PREHOOK: query: select * from orders join customer on customer.id = orders.customer_id order by orders.amount, customer.name limit 3
+PREHOOK: query: select * from orders join customer on customer.id = orders.customer_id order by orders.customer_id, customer.name limit 3
PREHOOK: type: QUERY
PREHOOK: Input: default@customer
PREHOOK: Input: default@orders
#### A masked pattern was here ####
-POSTHOOK: query: select * from orders join customer on customer.id = orders.customer_id order by orders.amount, customer.name limit 3
+POSTHOOK: query: select * from orders join customer on customer.id = orders.customer_id order by orders.customer_id, customer.name limit 3
POSTHOOK: type: QUERY
POSTHOOK: Input: default@customer
POSTHOOK: Input: default@orders
#### A masked pattern was here ####
-3 30 3 Smith smith@email.com
-3 40 3 Smith smith@email.com
+1 100 1 Robinson robinson@email.com
1 50 1 Robinson robinson@email.com
-PREHOOK: query: select 'positive: nulls first'
+2 200 2 Jones jones@email.com
+PREHOOK: query: select 'negative: nulls first'
PREHOOK: type: QUERY
PREHOOK: Input: _dummy_database@_dummy_table
#### A masked pattern was here ####
-POSTHOOK: query: select 'positive: nulls first'
+POSTHOOK: query: select 'negative: nulls first'
POSTHOOK: type: QUERY
POSTHOOK: Input: _dummy_database@_dummy_table
#### A masked pattern was here ####
-positive: nulls first
+negative: nulls first
PREHOOK: query: explain select * from customer join orders on orders.customer_id = customer.id order by customer_id nulls first limit 1
PREHOOK: type: QUERY
PREHOOK: Input: default@customer
@@ -1033,23 +1039,17 @@ STAGE PLANS:
Filter Operator
predicate: customer_id is not null (type: boolean)
Statistics: Num rows: 5 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE
- Top N Key Operator
- sort order: +
- keys: customer_id (type: int)
- null sort order: a
+ Select Operator
+ expressions: customer_id (type: int), amount (type: int)
+ outputColumnNames: _col0, _col1
Statistics: Num rows: 5 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE
- top n: 1
- Select Operator
- expressions: customer_id (type: int), amount (type: int)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 5 Data size: 36 Basic stats: COMPLETE Column stats: COMPLETE
- Reduce Output Operator
- key expressions: _col0 (type: int)
- null sort order: z
- sort order: +
- Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 5 Data size: 36 Basic stats: COMPLETE Column stats: COMPLETE
- value expressions: _col1 (type: int)
+ Reduce Output Operator
+ key expressions: _col0 (type: int)
+ null sort order: z
+ sort order: +
+ Map-reduce partition columns: _col0 (type: int)
+ Statistics: Num rows: 5 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col1 (type: int)
Execution mode: vectorized, llap
LLAP IO: all inputs
Reducer 2
@@ -1062,13 +1062,19 @@ STAGE PLANS:
0 _col0 (type: int)
1 _col0 (type: int)
outputColumnNames: _col0, _col1, _col2, _col3, _col4
- Statistics: Num rows: 5 Data size: 1016 Basic stats: COMPLETE Column stats: COMPLETE
- Reduce Output Operator
- key expressions: _col3 (type: int)
- null sort order: a
+ Statistics: Num rows: 5 Data size: 1020 Basic stats: COMPLETE Column stats: COMPLETE
+ Top N Key Operator
sort order: +
- Statistics: Num rows: 5 Data size: 1016 Basic stats: COMPLETE Column stats: COMPLETE
- value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col4 (type: int)
+ keys: _col3 (type: int)
+ null sort order: a
+ Statistics: Num rows: 5 Data size: 1020 Basic stats: COMPLETE Column stats: COMPLETE
+ top n: 1
+ Reduce Output Operator
+ key expressions: _col3 (type: int)
+ null sort order: a
+ sort order: +
+ Statistics: Num rows: 5 Data size: 1020 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col4 (type: int)
Reducer 3
Execution mode: vectorized, llap
Reduce Operator Tree:
diff --git a/ql/src/test/results/clientpositive/llap/topnkey_inner_join2.q.out b/ql/src/test/results/clientpositive/llap/topnkey_inner_join2.q.out
index 5a32d03..b30ae3c 100644
--- a/ql/src/test/results/clientpositive/llap/topnkey_inner_join2.q.out
+++ b/ql/src/test/results/clientpositive/llap/topnkey_inner_join2.q.out
@@ -243,7 +243,7 @@ PREHOOK: query: explain select name, city
from customer join address
on customer.address_id = address.id
and name in ('Joe', 'Robert','Heisenberg')
- order by customer.id
+ order by customer.address_id
limit 3
PREHOOK: type: QUERY
PREHOOK: Input: default@address
@@ -253,7 +253,7 @@ POSTHOOK: query: explain select name, city
from customer join address
on customer.address_id = address.id
and name in ('Joe', 'Robert','Heisenberg')
- order by customer.id
+ order by customer.address_id
limit 3
POSTHOOK: type: QUERY
POSTHOOK: Input: default@address
@@ -277,27 +277,27 @@ STAGE PLANS:
TableScan
alias: customer
filterExpr: ((name) IN ('Joe ', 'Robert ', 'Heisenberg ') and address_id is not null) (type: boolean)
- Statistics: Num rows: 6 Data size: 630 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 6 Data size: 582 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: ((name) IN ('Joe ', 'Robert ', 'Heisenberg ') and address_id is not null) (type: boolean)
- Statistics: Num rows: 3 Data size: 315 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 3 Data size: 291 Basic stats: COMPLETE Column stats: COMPLETE
Top N Key Operator
sort order: +
- keys: id (type: bigint)
+ keys: address_id (type: bigint)
null sort order: z
- Statistics: Num rows: 3 Data size: 315 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 3 Data size: 291 Basic stats: COMPLETE Column stats: COMPLETE
top n: 3
Select Operator
- expressions: id (type: bigint), address_id (type: bigint), name (type: char(20))
- outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 3 Data size: 315 Basic stats: COMPLETE Column stats: COMPLETE
+ expressions: address_id (type: bigint), name (type: char(20))
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 3 Data size: 291 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
- key expressions: _col1 (type: bigint)
+ key expressions: _col0 (type: bigint)
null sort order: z
sort order: +
- Map-reduce partition columns: _col1 (type: bigint)
- Statistics: Num rows: 3 Data size: 315 Basic stats: COMPLETE Column stats: COMPLETE
- value expressions: _col0 (type: bigint), _col2 (type: char(20))
+ Map-reduce partition columns: _col0 (type: bigint)
+ Statistics: Num rows: 3 Data size: 291 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col1 (type: char(20))
Execution mode: vectorized, llap
LLAP IO: all inputs
Map 4
@@ -325,12 +325,12 @@ STAGE PLANS:
condition map:
Inner Join 0 to 1
keys:
- 0 _col1 (type: bigint)
+ 0 _col0 (type: bigint)
1 _col0 (type: bigint)
- outputColumnNames: _col0, _col2, _col4
+ outputColumnNames: _col0, _col1, _col3
Statistics: Num rows: 3 Data size: 567 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
- expressions: _col2 (type: char(20)), _col4 (type: varchar(60)), _col0 (type: bigint)
+ expressions: _col1 (type: char(20)), _col3 (type: varchar(60)), _col0 (type: bigint)
outputColumnNames: _col0, _col1, _col2
Statistics: Num rows: 3 Data size: 567 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
@@ -367,7 +367,7 @@ PREHOOK: query: select name, city
from customer join address
on customer.address_id = address.id
and name in ('Joe', 'Robert','Heisenberg')
- order by customer.id
+ order by customer.address_id
limit 3
PREHOOK: type: QUERY
PREHOOK: Input: default@address
@@ -377,7 +377,7 @@ POSTHOOK: query: select name, city
from customer join address
on customer.address_id = address.id
and name in ('Joe', 'Robert','Heisenberg')
- order by customer.id
+ order by customer.address_id
limit 3
POSTHOOK: type: QUERY
POSTHOOK: Input: default@address
diff --git a/ql/src/test/results/clientpositive/perf/tez/constraints/mv_query44.q.out b/ql/src/test/results/clientpositive/perf/tez/constraints/mv_query44.q.out
index ffd4720..5d03ec0 100644
--- a/ql/src/test/results/clientpositive/perf/tez/constraints/mv_query44.q.out
+++ b/ql/src/test/results/clientpositive/perf/tez/constraints/mv_query44.q.out
@@ -20,7 +20,7 @@ POSTHOOK: Input: default@store_sales
POSTHOOK: Output: database:default
POSTHOOK: Output: default@mv_store_sales_item_customer
POSTHOOK: Output: default@mv_store_sales_item_customer
-Warning: Shuffle Join MERGEJOIN[114][tables = [$hdt$_1, $hdt$_2]] in Stage 'Reducer 3' is a cross product
+Warning: Shuffle Join MERGEJOIN[112][tables = [$hdt$_1, $hdt$_2]] in Stage 'Reducer 3' is a cross product
PREHOOK: query: explain
select asceding.rnk, i1.i_product_name best_performing, i2.i_product_name worst_performing
from(select *
@@ -113,114 +113,114 @@ Stage-0
limit:100
Stage-1
Reducer 8 vectorized
- File Output Operator [FS_151]
- Limit [LIM_150] (rows=100 width=218)
+ File Output Operator [FS_149]
+ Limit [LIM_148] (rows=100 width=218)
Number of rows:100
- Select Operator [SEL_149] (rows=6951 width=218)
+ Select Operator [SEL_147] (rows=6951 width=218)
Output:["_col0","_col1","_col2"]
<-Reducer 7 [SIMPLE_EDGE]
SHUFFLE [RS_70]
Select Operator [SEL_69] (rows=6951 width=218)
Output:["_col0","_col1","_col2"]
- Merge Join Operator [MERGEJOIN_118] (rows=6951 width=218)
- Conds:RS_66._col2=RS_148._col0(Inner),Output:["_col1","_col5","_col7"]
- <-Map 11 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_148]
- PartitionCols:_col0
- Select Operator [SEL_146] (rows=462000 width=111)
- Output:["_col0","_col1"]
- TableScan [TS_56] (rows=462000 width=111)
- default@item,i1,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_sk","i_product_name"]
- <-Reducer 6 [SIMPLE_EDGE]
- SHUFFLE [RS_66]
- PartitionCols:_col2
- Merge Join Operator [MERGEJOIN_117] (rows=6951 width=115)
- Conds:RS_63._col0=RS_147._col0(Inner),Output:["_col1","_col2","_col5"]
- <-Map 11 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_147]
- PartitionCols:_col0
- Please refer to the previous Select Operator [SEL_146]
- <-Reducer 5 [SIMPLE_EDGE]
- SHUFFLE [RS_63]
- PartitionCols:_col0
- Top N Key Operator [TNK_101] (rows=6951 width=12)
- keys:_col1,top n:100
- Merge Join Operator [MERGEJOIN_116] (rows=6951 width=12)
- Conds:RS_140._col1=RS_145._col1(Inner),Output:["_col0","_col1","_col2"]
+ Top N Key Operator [TNK_99] (rows=6951 width=218)
+ keys:_col1,top n:100
+ Merge Join Operator [MERGEJOIN_116] (rows=6951 width=218)
+ Conds:RS_66._col2=RS_146._col0(Inner),Output:["_col1","_col5","_col7"]
+ <-Map 11 [SIMPLE_EDGE] vectorized
+ SHUFFLE [RS_146]
+ PartitionCols:_col0
+ Select Operator [SEL_144] (rows=462000 width=111)
+ Output:["_col0","_col1"]
+ TableScan [TS_56] (rows=462000 width=111)
+ default@item,i1,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_sk","i_product_name"]
+ <-Reducer 6 [SIMPLE_EDGE]
+ SHUFFLE [RS_66]
+ PartitionCols:_col2
+ Merge Join Operator [MERGEJOIN_115] (rows=6951 width=115)
+ Conds:RS_63._col0=RS_145._col0(Inner),Output:["_col1","_col2","_col5"]
+ <-Map 11 [SIMPLE_EDGE] vectorized
+ SHUFFLE [RS_145]
+ PartitionCols:_col0
+ Please refer to the previous Select Operator [SEL_144]
+ <-Reducer 5 [SIMPLE_EDGE]
+ SHUFFLE [RS_63]
+ PartitionCols:_col0
+ Merge Join Operator [MERGEJOIN_114] (rows=6951 width=12)
+ Conds:RS_138._col1=RS_143._col1(Inner),Output:["_col0","_col1","_col2"]
<-Reducer 4 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_140]
+ SHUFFLE [RS_138]
PartitionCols:_col1
- Select Operator [SEL_139] (rows=6951 width=8)
+ Select Operator [SEL_137] (rows=6951 width=8)
Output:["_col0","_col1"]
- Filter Operator [FIL_138] (rows=6951 width=116)
+ Filter Operator [FIL_136] (rows=6951 width=116)
predicate:(rank_window_0 < 11)
- PTF Operator [PTF_137] (rows=20854 width=116)
+ PTF Operator [PTF_135] (rows=20854 width=116)
Function definitions:[{},{"name:":"windowingtablefunction","order by:":"_col1 ASC NULLS LAST","partition by:":"0"}]
- Select Operator [SEL_136] (rows=20854 width=116)
+ Select Operator [SEL_134] (rows=20854 width=116)
Output:["_col0","_col1"]
<-Reducer 3 [SIMPLE_EDGE]
SHUFFLE [RS_21]
PartitionCols:0
- Top N Key Operator [TNK_102] (rows=20854 width=228)
+ Top N Key Operator [TNK_100] (rows=20854 width=228)
keys:_col1,top n:11
Filter Operator [FIL_20] (rows=20854 width=228)
predicate:(_col1 > (0.9 * _col2))
- Merge Join Operator [MERGEJOIN_114] (rows=62562 width=228)
+ Merge Join Operator [MERGEJOIN_112] (rows=62562 width=228)
Conds:(Inner),Output:["_col0","_col1","_col2"]
<-Reducer 10 [CUSTOM_SIMPLE_EDGE] vectorized
- PARTITION_ONLY_SHUFFLE [RS_135]
- Select Operator [SEL_134] (rows=1 width=112)
+ PARTITION_ONLY_SHUFFLE [RS_133]
+ Select Operator [SEL_132] (rows=1 width=112)
Output:["_col0"]
- Filter Operator [FIL_133] (rows=1 width=120)
+ Filter Operator [FIL_131] (rows=1 width=120)
predicate:CAST( (_col1 / _col2) AS decimal(11,6)) is not null
- Select Operator [SEL_132] (rows=1 width=120)
+ Select Operator [SEL_130] (rows=1 width=120)
Output:["_col1","_col2"]
- Group By Operator [GBY_131] (rows=1 width=124)
+ Group By Operator [GBY_129] (rows=1 width=124)
Output:["_col0","_col1","_col2"],aggregations:["sum(VALUE._col0)","count(VALUE._col1)"],keys:KEY._col0
<-Map 1 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_126]
+ SHUFFLE [RS_124]
PartitionCols:_col0
- Group By Operator [GBY_124] (rows=258 width=124)
+ Group By Operator [GBY_122] (rows=258 width=124)
Output:["_col0","_col1","_col2"],aggregations:["sum(_col1)","count(_col1)"],keys:true
- Select Operator [SEL_122] (rows=287946 width=114)
+ Select Operator [SEL_120] (rows=287946 width=114)
Output:["_col1"]
- Filter Operator [FIL_120] (rows=287946 width=114)
+ Filter Operator [FIL_118] (rows=287946 width=114)
predicate:(ss_hdemo_sk is null and (ss_store_sk = 410))
TableScan [TS_0] (rows=575995635 width=114)
default@store_sales,ss1,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_item_sk","ss_store_sk","ss_net_profit","ss_hdemo_sk"]
<-Reducer 2 [CUSTOM_SIMPLE_EDGE] vectorized
- PARTITION_ONLY_SHUFFLE [RS_130]
- Select Operator [SEL_129] (rows=62562 width=116)
+ PARTITION_ONLY_SHUFFLE [RS_128]
+ Select Operator [SEL_127] (rows=62562 width=116)
Output:["_col0","_col1"]
- Filter Operator [FIL_128] (rows=62562 width=124)
+ Filter Operator [FIL_126] (rows=62562 width=124)
predicate:CAST( (_col1 / _col2) AS decimal(11,6)) is not null
- Group By Operator [GBY_127] (rows=62562 width=124)
+ Group By Operator [GBY_125] (rows=62562 width=124)
Output:["_col0","_col1","_col2"],aggregations:["sum(VALUE._col0)","count(VALUE._col1)"],keys:KEY._col0
<-Map 1 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_125]
+ SHUFFLE [RS_123]
PartitionCols:_col0
- Group By Operator [GBY_123] (rows=3199976 width=124)
+ Group By Operator [GBY_121] (rows=3199976 width=124)
Output:["_col0","_col1","_col2"],aggregations:["sum(ss_net_profit)","count(ss_net_profit)"],keys:ss_item_sk
- Select Operator [SEL_121] (rows=6399952 width=114)
+ Select Operator [SEL_119] (rows=6399952 width=114)
Output:["ss_item_sk","ss_net_profit"]
- Filter Operator [FIL_119] (rows=6399952 width=114)
+ Filter Operator [FIL_117] (rows=6399952 width=114)
predicate:(ss_store_sk = 410)
Please refer to the previous TableScan [TS_0]
<-Reducer 9 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_145]
+ SHUFFLE [RS_143]
PartitionCols:_col1
- Select Operator [SEL_144] (rows=6951 width=8)
+ Select Operator [SEL_142] (rows=6951 width=8)
Output:["_col0","_col1"]
- Filter Operator [FIL_143] (rows=6951 width=116)
+ Filter Operator [FIL_141] (rows=6951 width=116)
predicate:(rank_window_0 < 11)
- PTF Operator [PTF_142] (rows=20854 width=116)
+ PTF Operator [PTF_140] (rows=20854 width=116)
Function definitions:[{},{"name:":"windowingtablefunction","order by:":"_col1 DESC NULLS FIRST","partition by:":"0"}]
- Select Operator [SEL_141] (rows=20854 width=116)
+ Select Operator [SEL_139] (rows=20854 width=116)
Output:["_col0","_col1"]
<-Reducer 3 [SIMPLE_EDGE]
SHUFFLE [RS_49]
PartitionCols:0
- Top N Key Operator [TNK_103] (rows=20854 width=228)
+ Top N Key Operator [TNK_101] (rows=20854 width=228)
keys:_col1,top n:11
Please refer to the previous Filter Operator [FIL_20]
diff --git a/ql/src/test/results/clientpositive/perf/tez/constraints/query44.q.out b/ql/src/test/results/clientpositive/perf/tez/constraints/query44.q.out
index 83ff93c..5358688 100644
--- a/ql/src/test/results/clientpositive/perf/tez/constraints/query44.q.out
+++ b/ql/src/test/results/clientpositive/perf/tez/constraints/query44.q.out
@@ -1,4 +1,4 @@
-Warning: Shuffle Join MERGEJOIN[114][tables = [$hdt$_1, $hdt$_2]] in Stage 'Reducer 3' is a cross product
+Warning: Shuffle Join MERGEJOIN[112][tables = [$hdt$_1, $hdt$_2]] in Stage 'Reducer 3' is a cross product
PREHOOK: query: explain
select asceding.rnk, i1.i_product_name best_performing, i2.i_product_name worst_performing
from(select *
@@ -91,114 +91,114 @@ Stage-0
limit:100
Stage-1
Reducer 8 vectorized
- File Output Operator [FS_151]
- Limit [LIM_150] (rows=100 width=218)
+ File Output Operator [FS_149]
+ Limit [LIM_148] (rows=100 width=218)
Number of rows:100
- Select Operator [SEL_149] (rows=6951 width=218)
+ Select Operator [SEL_147] (rows=6951 width=218)
Output:["_col0","_col1","_col2"]
<-Reducer 7 [SIMPLE_EDGE]
SHUFFLE [RS_70]
Select Operator [SEL_69] (rows=6951 width=218)
Output:["_col0","_col1","_col2"]
- Merge Join Operator [MERGEJOIN_118] (rows=6951 width=218)
- Conds:RS_66._col2=RS_148._col0(Inner),Output:["_col1","_col5","_col7"]
- <-Map 11 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_148]
- PartitionCols:_col0
- Select Operator [SEL_146] (rows=462000 width=111)
- Output:["_col0","_col1"]
- TableScan [TS_56] (rows=462000 width=111)
- default@item,i1,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_sk","i_product_name"]
- <-Reducer 6 [SIMPLE_EDGE]
- SHUFFLE [RS_66]
- PartitionCols:_col2
- Merge Join Operator [MERGEJOIN_117] (rows=6951 width=115)
- Conds:RS_63._col0=RS_147._col0(Inner),Output:["_col1","_col2","_col5"]
- <-Map 11 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_147]
- PartitionCols:_col0
- Please refer to the previous Select Operator [SEL_146]
- <-Reducer 5 [SIMPLE_EDGE]
- SHUFFLE [RS_63]
- PartitionCols:_col0
- Top N Key Operator [TNK_101] (rows=6951 width=12)
- keys:_col1,top n:100
- Merge Join Operator [MERGEJOIN_116] (rows=6951 width=12)
- Conds:RS_140._col1=RS_145._col1(Inner),Output:["_col0","_col1","_col2"]
+ Top N Key Operator [TNK_99] (rows=6951 width=218)
+ keys:_col1,top n:100
+ Merge Join Operator [MERGEJOIN_116] (rows=6951 width=218)
+ Conds:RS_66._col2=RS_146._col0(Inner),Output:["_col1","_col5","_col7"]
+ <-Map 11 [SIMPLE_EDGE] vectorized
+ SHUFFLE [RS_146]
+ PartitionCols:_col0
+ Select Operator [SEL_144] (rows=462000 width=111)
+ Output:["_col0","_col1"]
+ TableScan [TS_56] (rows=462000 width=111)
+ default@item,i1,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_sk","i_product_name"]
+ <-Reducer 6 [SIMPLE_EDGE]
+ SHUFFLE [RS_66]
+ PartitionCols:_col2
+ Merge Join Operator [MERGEJOIN_115] (rows=6951 width=115)
+ Conds:RS_63._col0=RS_145._col0(Inner),Output:["_col1","_col2","_col5"]
+ <-Map 11 [SIMPLE_EDGE] vectorized
+ SHUFFLE [RS_145]
+ PartitionCols:_col0
+ Please refer to the previous Select Operator [SEL_144]
+ <-Reducer 5 [SIMPLE_EDGE]
+ SHUFFLE [RS_63]
+ PartitionCols:_col0
+ Merge Join Operator [MERGEJOIN_114] (rows=6951 width=12)
+ Conds:RS_138._col1=RS_143._col1(Inner),Output:["_col0","_col1","_col2"]
<-Reducer 4 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_140]
+ SHUFFLE [RS_138]
PartitionCols:_col1
- Select Operator [SEL_139] (rows=6951 width=8)
+ Select Operator [SEL_137] (rows=6951 width=8)
Output:["_col0","_col1"]
- Filter Operator [FIL_138] (rows=6951 width=116)
+ Filter Operator [FIL_136] (rows=6951 width=116)
predicate:(rank_window_0 < 11)
- PTF Operator [PTF_137] (rows=20854 width=116)
+ PTF Operator [PTF_135] (rows=20854 width=116)
Function definitions:[{},{"name:":"windowingtablefunction","order by:":"_col1 ASC NULLS LAST","partition by:":"0"}]
- Select Operator [SEL_136] (rows=20854 width=116)
+ Select Operator [SEL_134] (rows=20854 width=116)
Output:["_col0","_col1"]
<-Reducer 3 [SIMPLE_EDGE]
SHUFFLE [RS_21]
PartitionCols:0
- Top N Key Operator [TNK_102] (rows=20854 width=228)
+ Top N Key Operator [TNK_100] (rows=20854 width=228)
keys:_col1,top n:11
Filter Operator [FIL_20] (rows=20854 width=228)
predicate:(_col1 > (0.9 * _col2))
- Merge Join Operator [MERGEJOIN_114] (rows=62562 width=228)
+ Merge Join Operator [MERGEJOIN_112] (rows=62562 width=228)
Conds:(Inner),Output:["_col0","_col1","_col2"]
<-Reducer 10 [CUSTOM_SIMPLE_EDGE] vectorized
- PARTITION_ONLY_SHUFFLE [RS_135]
- Select Operator [SEL_134] (rows=1 width=112)
+ PARTITION_ONLY_SHUFFLE [RS_133]
+ Select Operator [SEL_132] (rows=1 width=112)
Output:["_col0"]
- Filter Operator [FIL_133] (rows=1 width=120)
+ Filter Operator [FIL_131] (rows=1 width=120)
predicate:CAST( (_col1 / _col2) AS decimal(11,6)) is not null
- Select Operator [SEL_132] (rows=1 width=120)
+ Select Operator [SEL_130] (rows=1 width=120)
Output:["_col1","_col2"]
- Group By Operator [GBY_131] (rows=1 width=124)
+ Group By Operator [GBY_129] (rows=1 width=124)
Output:["_col0","_col1","_col2"],aggregations:["sum(VALUE._col0)","count(VALUE._col1)"],keys:KEY._col0
<-Map 1 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_126]
+ SHUFFLE [RS_124]
PartitionCols:_col0
- Group By Operator [GBY_124] (rows=258 width=124)
+ Group By Operator [GBY_122] (rows=258 width=124)
Output:["_col0","_col1","_col2"],aggregations:["sum(_col1)","count(_col1)"],keys:true
- Select Operator [SEL_122] (rows=287946 width=114)
+ Select Operator [SEL_120] (rows=287946 width=114)
Output:["_col1"]
- Filter Operator [FIL_120] (rows=287946 width=114)
+ Filter Operator [FIL_118] (rows=287946 width=114)
predicate:(ss_hdemo_sk is null and (ss_store_sk = 410))
TableScan [TS_0] (rows=575995635 width=114)
default@store_sales,ss1,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_item_sk","ss_store_sk","ss_net_profit","ss_hdemo_sk"]
<-Reducer 2 [CUSTOM_SIMPLE_EDGE] vectorized
- PARTITION_ONLY_SHUFFLE [RS_130]
- Select Operator [SEL_129] (rows=62562 width=116)
+ PARTITION_ONLY_SHUFFLE [RS_128]
+ Select Operator [SEL_127] (rows=62562 width=116)
Output:["_col0","_col1"]
- Filter Operator [FIL_128] (rows=62562 width=124)
+ Filter Operator [FIL_126] (rows=62562 width=124)
predicate:CAST( (_col1 / _col2) AS decimal(11,6)) is not null
- Group By Operator [GBY_127] (rows=62562 width=124)
+ Group By Operator [GBY_125] (rows=62562 width=124)
Output:["_col0","_col1","_col2"],aggregations:["sum(VALUE._col0)","count(VALUE._col1)"],keys:KEY._col0
<-Map 1 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_125]
+ SHUFFLE [RS_123]
PartitionCols:_col0
- Group By Operator [GBY_123] (rows=3199976 width=124)
+ Group By Operator [GBY_121] (rows=3199976 width=124)
Output:["_col0","_col1","_col2"],aggregations:["sum(ss_net_profit)","count(ss_net_profit)"],keys:ss_item_sk
- Select Operator [SEL_121] (rows=6399952 width=114)
+ Select Operator [SEL_119] (rows=6399952 width=114)
Output:["ss_item_sk","ss_net_profit"]
- Filter Operator [FIL_119] (rows=6399952 width=114)
+ Filter Operator [FIL_117] (rows=6399952 width=114)
predicate:(ss_store_sk = 410)
Please refer to the previous TableScan [TS_0]
<-Reducer 9 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_145]
+ SHUFFLE [RS_143]
PartitionCols:_col1
- Select Operator [SEL_144] (rows=6951 width=8)
+ Select Operator [SEL_142] (rows=6951 width=8)
Output:["_col0","_col1"]
- Filter Operator [FIL_143] (rows=6951 width=116)
+ Filter Operator [FIL_141] (rows=6951 width=116)
predicate:(rank_window_0 < 11)
- PTF Operator [PTF_142] (rows=20854 width=116)
+ PTF Operator [PTF_140] (rows=20854 width=116)
Function definitions:[{},{"name:":"windowingtablefunction","order by:":"_col1 DESC NULLS FIRST","partition by:":"0"}]
- Select Operator [SEL_141] (rows=20854 width=116)
+ Select Operator [SEL_139] (rows=20854 width=116)
Output:["_col0","_col1"]
<-Reducer 3 [SIMPLE_EDGE]
SHUFFLE [RS_49]
PartitionCols:0
- Top N Key Operator [TNK_103] (rows=20854 width=228)
+ Top N Key Operator [TNK_101] (rows=20854 width=228)
keys:_col1,top n:11
Please refer to the previous Filter Operator [FIL_20]
diff --git a/ql/src/test/results/clientpositive/perf/tez/constraints/query65.q.out b/ql/src/test/results/clientpositive/perf/tez/constraints/query65.q.out
index 9e767e2..a26ef09 100644
--- a/ql/src/test/results/clientpositive/perf/tez/constraints/query65.q.out
+++ b/ql/src/test/results/clientpositive/perf/tez/constraints/query65.q.out
@@ -82,10 +82,10 @@ Stage-0
limit:100
Stage-1
Reducer 7 vectorized
- File Output Operator [FS_167]
- Limit [LIM_166] (rows=100 width=702)
+ File Output Operator [FS_166]
+ Limit [LIM_165] (rows=100 width=702)
Number of rows:100
- Select Operator [SEL_165] (rows=65392 width=700)
+ Select Operator [SEL_164] (rows=65392 width=700)
Output:["_col0","_col1","_col2","_col3","_col4","_col5"]
<-Reducer 6 [SIMPLE_EDGE]
SHUFFLE [RS_51]
@@ -93,94 +93,92 @@ Stage-0
Output:["_col0","_col1","_col2","_col3","_col4","_col5"]
Top N Key Operator [TNK_80] (rows=65392 width=704)
keys:_col6, _col8,top n:100
- Merge Join Operator [MERGEJOIN_139] (rows=65392 width=704)
- Conds:RS_47._col1=RS_164._col0(Inner),Output:["_col2","_col6","_col8","_col9","_col10","_col11"]
+ Merge Join Operator [MERGEJOIN_138] (rows=65392 width=704)
+ Conds:RS_47._col1=RS_163._col0(Inner),Output:["_col2","_col6","_col8","_col9","_col10","_col11"]
<-Map 12 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_164]
+ SHUFFLE [RS_163]
PartitionCols:_col0
- Select Operator [SEL_163] (rows=462000 width=511)
+ Select Operator [SEL_162] (rows=462000 width=511)
Output:["_col0","_col1","_col2","_col3","_col4"]
TableScan [TS_38] (rows=462000 width=511)
default@item,item,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_sk","i_item_desc","i_current_price","i_wholesale_cost","i_brand"]
<-Reducer 5 [SIMPLE_EDGE]
SHUFFLE [RS_47]
PartitionCols:_col1
- Top N Key Operator [TNK_81] (rows=65392 width=204)
- keys:_col6,top n:100
- Merge Join Operator [MERGEJOIN_138] (rows=65392 width=204)
- Conds:RS_44._col0=RS_162._col0(Inner),Output:["_col1","_col2","_col6"]
- <-Map 11 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_162]
- PartitionCols:_col0
- Select Operator [SEL_161] (rows=1704 width=92)
- Output:["_col0","_col1"]
- TableScan [TS_36] (rows=1704 width=92)
- default@store,store,Tbl:COMPLETE,Col:COMPLETE,Output:["s_store_sk","s_store_name"]
- <-Reducer 4 [SIMPLE_EDGE]
- SHUFFLE [RS_44]
- PartitionCols:_col0
- Filter Operator [FIL_43] (rows=65392 width=231)
- predicate:(_col2 <= _col4)
- Merge Join Operator [MERGEJOIN_137] (rows=196176 width=231)
- Conds:RS_154._col0=RS_160._col0(Inner),Output:["_col0","_col1","_col2","_col4"]
- <-Reducer 3 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_154]
- PartitionCols:_col0
- Filter Operator [FIL_152] (rows=184637 width=118)
- predicate:_col2 is not null
- Group By Operator [GBY_151] (rows=184637 width=118)
- Output:["_col0","_col1","_col2"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1
- <-Reducer 2 [SIMPLE_EDGE]
- SHUFFLE [RS_11]
- PartitionCols:_col0, _col1
- Group By Operator [GBY_10] (rows=6093021 width=118)
- Output:["_col0","_col1","_col2"],aggregations:["sum(_col3)"],keys:_col2, _col1
- Merge Join Operator [MERGEJOIN_135] (rows=91197860 width=89)
- Conds:RS_150._col0=RS_142._col0(Inner),Output:["_col1","_col2","_col3"]
- <-Map 9 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_142]
- PartitionCols:_col0
- Select Operator [SEL_141] (rows=317 width=4)
- Output:["_col0"]
- Filter Operator [FIL_140] (rows=317 width=8)
- predicate:d_month_seq BETWEEN 1212 AND 1223
- TableScan [TS_3] (rows=73049 width=8)
- default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_month_seq"]
- <-Map 1 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_150]
- PartitionCols:_col0
- Select Operator [SEL_149] (rows=525329897 width=118)
- Output:["_col0","_col1","_col2","_col3"]
- Filter Operator [FIL_148] (rows=525329897 width=118)
- predicate:(ss_sold_date_sk is not null and ss_store_sk is not null and ss_sold_date_sk BETWEEN DynamicValue(RS_7_date_dim_d_date_sk_min) AND DynamicValue(RS_7_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_7_date_dim_d_date_sk_bloom_filter)))
- TableScan [TS_0] (rows=575995635 width=118)
- default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_item_sk","ss_store_sk","ss_sales_price"]
- <-Reducer 10 [BROADCAST_EDGE] vectorized
- BROADCAST [RS_147]
- Group By Operator [GBY_146] (rows=1 width=12)
- Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"]
- <-Map 9 [CUSTOM_SIMPLE_EDGE] vectorized
- SHUFFLE [RS_145]
- Group By Operator [GBY_144] (rows=1 width=12)
- Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"]
- Select Operator [SEL_143] (rows=317 width=4)
- Output:["_col0"]
- Please refer to the previous Select Operator [SEL_141]
- <-Reducer 8 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_160]
- PartitionCols:_col0
- Select Operator [SEL_159] (rows=17 width=115)
- Output:["_col0","_col1"]
- Filter Operator [FIL_158] (rows=17 width=123)
- predicate:CAST( (_col1 / _col2) AS decimal(21,6)) is not null
- Group By Operator [GBY_157] (rows=17 width=123)
- Output:["_col0","_col1","_col2"],aggregations:["sum(VALUE._col0)","count(VALUE._col1)"],keys:KEY._col0
- <-Reducer 3 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_156]
- PartitionCols:_col0
- Group By Operator [GBY_155] (rows=17 width=123)
- Output:["_col0","_col1","_col2"],aggregations:["sum(_col2)","count(_col2)"],keys:_col1
- Select Operator [SEL_153] (rows=184637 width=118)
- Output:["_col1","_col2"]
- Please refer to the previous Group By Operator [GBY_151]
+ Merge Join Operator [MERGEJOIN_137] (rows=65392 width=204)
+ Conds:RS_44._col0=RS_161._col0(Inner),Output:["_col1","_col2","_col6"]
+ <-Map 11 [SIMPLE_EDGE] vectorized
+ SHUFFLE [RS_161]
+ PartitionCols:_col0
+ Select Operator [SEL_160] (rows=1704 width=92)
+ Output:["_col0","_col1"]
+ TableScan [TS_36] (rows=1704 width=92)
+ default@store,store,Tbl:COMPLETE,Col:COMPLETE,Output:["s_store_sk","s_store_name"]
+ <-Reducer 4 [SIMPLE_EDGE]
+ SHUFFLE [RS_44]
+ PartitionCols:_col0
+ Filter Operator [FIL_43] (rows=65392 width=231)
+ predicate:(_col2 <= _col4)
+ Merge Join Operator [MERGEJOIN_136] (rows=196176 width=231)
+ Conds:RS_153._col0=RS_159._col0(Inner),Output:["_col0","_col1","_col2","_col4"]
+ <-Reducer 3 [SIMPLE_EDGE] vectorized
+ SHUFFLE [RS_153]
+ PartitionCols:_col0
+ Filter Operator [FIL_151] (rows=184637 width=118)
+ predicate:_col2 is not null
+ Group By Operator [GBY_150] (rows=184637 width=118)
+ Output:["_col0","_col1","_col2"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1
+ <-Reducer 2 [SIMPLE_EDGE]
+ SHUFFLE [RS_11]
+ PartitionCols:_col0, _col1
+ Group By Operator [GBY_10] (rows=6093021 width=118)
+ Output:["_col0","_col1","_col2"],aggregations:["sum(_col3)"],keys:_col2, _col1
+ Merge Join Operator [MERGEJOIN_134] (rows=91197860 width=89)
+ Conds:RS_149._col0=RS_141._col0(Inner),Output:["_col1","_col2","_col3"]
+ <-Map 9 [SIMPLE_EDGE] vectorized
+ SHUFFLE [RS_141]
+ PartitionCols:_col0
+ Select Operator [SEL_140] (rows=317 width=4)
+ Output:["_col0"]
+ Filter Operator [FIL_139] (rows=317 width=8)
+ predicate:d_month_seq BETWEEN 1212 AND 1223
+ TableScan [TS_3] (rows=73049 width=8)
+ default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_month_seq"]
+ <-Map 1 [SIMPLE_EDGE] vectorized
+ SHUFFLE [RS_149]
+ PartitionCols:_col0
+ Select Operator [SEL_148] (rows=525329897 width=118)
+ Output:["_col0","_col1","_col2","_col3"]
+ Filter Operator [FIL_147] (rows=525329897 width=118)
+ predicate:(ss_sold_date_sk is not null and ss_store_sk is not null and ss_sold_date_sk BETWEEN DynamicValue(RS_7_date_dim_d_date_sk_min) AND DynamicValue(RS_7_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_7_date_dim_d_date_sk_bloom_filter)))
+ TableScan [TS_0] (rows=575995635 width=118)
+ default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_item_sk","ss_store_sk","ss_sales_price"]
+ <-Reducer 10 [BROADCAST_EDGE] vectorized
+ BROADCAST [RS_146]
+ Group By Operator [GBY_145] (rows=1 width=12)
+ Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"]
+ <-Map 9 [CUSTOM_SIMPLE_EDGE] vectorized
+ SHUFFLE [RS_144]
+ Group By Operator [GBY_143] (rows=1 width=12)
+ Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"]
+ Select Operator [SEL_142] (rows=317 width=4)
+ Output:["_col0"]
+ Please refer to the previous Select Operator [SEL_140]
+ <-Reducer 8 [SIMPLE_EDGE] vectorized
+ SHUFFLE [RS_159]
+ PartitionCols:_col0
+ Select Operator [SEL_158] (rows=17 width=115)
+ Output:["_col0","_col1"]
+ Filter Operator [FIL_157] (rows=17 width=123)
+ predicate:CAST( (_col1 / _col2) AS decimal(21,6)) is not null
+ Group By Operator [GBY_156] (rows=17 width=123)
+ Output:["_col0","_col1","_col2"],aggregations:["sum(VALUE._col0)","count(VALUE._col1)"],keys:KEY._col0
+ <-Reducer 3 [SIMPLE_EDGE] vectorized
+ SHUFFLE [RS_155]
+ PartitionCols:_col0
+ Group By Operator [GBY_154] (rows=17 width=123)
+ Output:["_col0","_col1","_col2"],aggregations:["sum(_col2)","count(_col2)"],keys:_col1
+ Select Operator [SEL_152] (rows=184637 width=118)
+ Output:["_col1","_col2"]
+ Please refer to the previous Group By Operator [GBY_150]
diff --git a/ql/src/test/results/clientpositive/perf/tez/constraints/query99.q.out b/ql/src/test/results/clientpositive/perf/tez/constraints/query99.q.out
index a8dbeac..423d107 100644
--- a/ql/src/test/results/clientpositive/perf/tez/constraints/query99.q.out
+++ b/ql/src/test/results/clientpositive/perf/tez/constraints/query99.q.out
@@ -95,16 +95,16 @@ Stage-0
limit:-1
Stage-1
Reducer 7 vectorized
- File Output Operator [FS_127]
- Limit [LIM_126] (rows=100 width=420)
+ File Output Operator [FS_125]
+ Limit [LIM_124] (rows=100 width=420)
Number of rows:100
- Select Operator [SEL_125] (rows=3869553 width=420)
+ Select Operator [SEL_123] (rows=3869553 width=420)
Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"]
<-Reducer 6 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_124]
- Select Operator [SEL_123] (rows=3869553 width=420)
+ SHUFFLE [RS_122]
+ Select Operator [SEL_121] (rows=3869553 width=420)
Output:["_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"]
- Group By Operator [GBY_122] (rows=3869553 width=321)
+ Group By Operator [GBY_120] (rows=3869553 width=321)
Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"],aggregations:["sum(VALUE._col0)","sum(VALUE._col1)","sum(VALUE._col2)","sum(VALUE._col3)","sum(VALUE._col4)"],keys:KEY._col0, KEY._col1, KEY._col2
<-Reducer 5 [SIMPLE_EDGE]
SHUFFLE [RS_26]
@@ -113,73 +113,71 @@ Stage-0
Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"],aggregations:["sum(_col4)","sum(_col5)","sum(_col6)","sum(_col7)","sum(_col8)"],keys:_col13, _col11, _col15
Top N Key Operator [TNK_56] (rows=15478212 width=301)
keys:_col13, _col11, _col15,top n:100
- Merge Join Operator [MERGEJOIN_104] (rows=15478212 width=301)
- Conds:RS_21._col1=RS_121._col0(Inner),Output:["_col4","_col5","_col6","_col7","_col8","_col11","_col13","_col15"]
+ Merge Join Operator [MERGEJOIN_102] (rows=15478212 width=301)
+ Conds:RS_21._col1=RS_119._col0(Inner),Output:["_col4","_col5","_col6","_col7","_col8","_col11","_col13","_col15"]
<-Map 12 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_121]
+ SHUFFLE [RS_119]
PartitionCols:_col0
- Select Operator [SEL_120] (rows=60 width=102)
+ Select Operator [SEL_118] (rows=60 width=102)
Output:["_col0","_col1"]
TableScan [TS_10] (rows=60 width=102)
default@call_center,call_center,Tbl:COMPLETE,Col:COMPLETE,Output:["cc_call_center_sk","cc_name"]
<-Reducer 4 [SIMPLE_EDGE]
SHUFFLE [RS_21]
PartitionCols:_col1
- Top N Key Operator [TNK_57] (rows=15478212 width=206)
- keys:_col13, _col11,top n:100
- Merge Join Operator [MERGEJOIN_103] (rows=15478212 width=206)
- Conds:RS_18._col3=RS_119._col0(Inner),Output:["_col1","_col4","_col5","_col6","_col7","_col8","_col11","_col13"]
- <-Map 11 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_119]
- PartitionCols:_col0
- Select Operator [SEL_118] (rows=27 width=103)
- Output:["_col0","_col1"]
- TableScan [TS_8] (rows=27 width=104)
- default@warehouse,warehouse,Tbl:COMPLETE,Col:COMPLETE,Output:["w_warehouse_sk","w_warehouse_name"]
- <-Reducer 3 [SIMPLE_EDGE]
- SHUFFLE [RS_18]
- PartitionCols:_col3
- Merge Join Operator [MERGEJOIN_102] (rows=15478212 width=111)
- Conds:RS_15._col2=RS_106._col0(Inner),Output:["_col1","_col3","_col4","_col5","_col6","_col7","_col8","_col11"]
- <-Map 9 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_106]
- PartitionCols:_col0
- Select Operator [SEL_105] (rows=1 width=88)
- Output:["_col0","_col1"]
- TableScan [TS_6] (rows=1 width=88)
- default@ship_mode,ship_mode,Tbl:COMPLETE,Col:COMPLETE,Output:["sm_ship_mode_sk","sm_type"]
- <-Reducer 2 [SIMPLE_EDGE]
- SHUFFLE [RS_15]
- PartitionCols:_col2
- Merge Join Operator [MERGEJOIN_101] (rows=46434637 width=31)
- Conds:RS_114._col0=RS_117._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"]
- <-Map 1 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_114]
- PartitionCols:_col0
- Select Operator [SEL_113] (rows=282273729 width=35)
- Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"]
- Filter Operator [FIL_112] (rows=282273729 width=19)
- predicate:(cs_warehouse_sk is not null and cs_ship_date_sk is not null and cs_ship_mode_sk is not null and cs_call_center_sk is not null and cs_ship_mode_sk BETWEEN DynamicValue(RS_16_ship_mode_sm_ship_mode_sk_min) AND DynamicValue(RS_16_ship_mode_sm_ship_mode_sk_max) and in_bloom_filter(cs_ship_mode_sk, DynamicValue(RS_16_ship_mode_sm_ship_mode_sk_bloom_filter)))
- TableScan [TS_0] (rows=287989836 width=19)
- default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["cs_sold_date_sk","cs_ship_date_sk","cs_call_center_sk","cs_ship_mode_sk","cs_warehouse_sk"]
- <-Reducer 10 [BROADCAST_EDGE] vectorized
- BROADCAST [RS_111]
- Group By Operator [GBY_110] (rows=1 width=12)
- Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"]
- <-Map 9 [CUSTOM_SIMPLE_EDGE] vectorized
- SHUFFLE [RS_109]
- Group By Operator [GBY_108] (rows=1 width=12)
- Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"]
- Select Operator [SEL_107] (rows=1 width=4)
- Output:["_col0"]
- Please refer to the previous Select Operator [SEL_105]
- <-Map 8 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_117]
- PartitionCols:_col0
- Select Operator [SEL_116] (rows=317 width=4)
- Output:["_col0"]
- Filter Operator [FIL_115] (rows=317 width=8)
- predicate:d_month_seq BETWEEN 1212 AND 1223
- TableScan [TS_3] (rows=73049 width=8)
- default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_month_seq"]
+ Merge Join Operator [MERGEJOIN_101] (rows=15478212 width=206)
+ Conds:RS_18._col3=RS_117._col0(Inner),Output:["_col1","_col4","_col5","_col6","_col7","_col8","_col11","_col13"]
+ <-Map 11 [SIMPLE_EDGE] vectorized
+ SHUFFLE [RS_117]
+ PartitionCols:_col0
+ Select Operator [SEL_116] (rows=27 width=103)
+ Output:["_col0","_col1"]
+ TableScan [TS_8] (rows=27 width=104)
+ default@warehouse,warehouse,Tbl:COMPLETE,Col:COMPLETE,Output:["w_warehouse_sk","w_warehouse_name"]
+ <-Reducer 3 [SIMPLE_EDGE]
+ SHUFFLE [RS_18]
+ PartitionCols:_col3
+ Merge Join Operator [MERGEJOIN_100] (rows=15478212 width=111)
+ Conds:RS_15._col2=RS_104._col0(Inner),Output:["_col1","_col3","_col4","_col5","_col6","_col7","_col8","_col11"]
+ <-Map 9 [SIMPLE_EDGE] vectorized
+ SHUFFLE [RS_104]
+ PartitionCols:_col0
+ Select Operator [SEL_103] (rows=1 width=88)
+ Output:["_col0","_col1"]
+ TableScan [TS_6] (rows=1 width=88)
+ default@ship_mode,ship_mode,Tbl:COMPLETE,Col:COMPLETE,Output:["sm_ship_mode_sk","sm_type"]
+ <-Reducer 2 [SIMPLE_EDGE]
+ SHUFFLE [RS_15]
+ PartitionCols:_col2
+ Merge Join Operator [MERGEJOIN_99] (rows=46434637 width=31)
+ Conds:RS_112._col0=RS_115._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"]
+ <-Map 1 [SIMPLE_EDGE] vectorized
+ SHUFFLE [RS_112]
+ PartitionCols:_col0
+ Select Operator [SEL_111] (rows=282273729 width=35)
+ Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"]
+ Filter Operator [FIL_110] (rows=282273729 width=19)
+ predicate:(cs_warehouse_sk is not null and cs_ship_date_sk is not null and cs_ship_mode_sk is not null and cs_call_center_sk is not null and cs_ship_mode_sk BETWEEN DynamicValue(RS_16_ship_mode_sm_ship_mode_sk_min) AND DynamicValue(RS_16_ship_mode_sm_ship_mode_sk_max) and in_bloom_filter(cs_ship_mode_sk, DynamicValue(RS_16_ship_mode_sm_ship_mode_sk_bloom_filter)))
+ TableScan [TS_0] (rows=287989836 width=19)
+ default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["cs_sold_date_sk","cs_ship_date_sk","cs_call_center_sk","cs_ship_mode_sk","cs_warehouse_sk"]
+ <-Reducer 10 [BROADCAST_EDGE] vectorized
+ BROADCAST [RS_109]
+ Group By Operator [GBY_108] (rows=1 width=12)
+ Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"]
+ <-Map 9 [CUSTOM_SIMPLE_EDGE] vectorized
+ SHUFFLE [RS_107]
+ Group By Operator [GBY_106] (rows=1 width=12)
+ Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"]
+ Select Operator [SEL_105] (rows=1 width=4)
+ Output:["_col0"]
+ Please refer to the previous Select Operator [SEL_103]
+ <-Map 8 [SIMPLE_EDGE] vectorized
+ SHUFFLE [RS_115]
+ PartitionCols:_col0
+ Select Operator [SEL_114] (rows=317 width=4)
+ Output:["_col0"]
+ Filter Operator [FIL_113] (rows=317 width=8)
+ predicate:d_month_seq BETWEEN 1212 AND 1223
+ TableScan [TS_3] (rows=73049 width=8)
+ default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_month_seq"]