You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@hive.apache.org by vg...@apache.org on 2018/08/07 19:27:01 UTC
[3/3] hive git commit: HIVE-20320: Turn on
hive.optimize.remove.sq_count_check flag (Vineet Garg,
reviewed by Ashutosh Chauhan)
HIVE-20320: Turn on hive.optimize.remove.sq_count_check flag (Vineet Garg, reviewed by Ashutosh Chauhan)
Project: http://git-wip-us.apache.org/repos/asf/hive/repo
Commit: http://git-wip-us.apache.org/repos/asf/hive/commit/d4a8625d
Tree: http://git-wip-us.apache.org/repos/asf/hive/tree/d4a8625d
Diff: http://git-wip-us.apache.org/repos/asf/hive/diff/d4a8625d
Branch: refs/heads/master
Commit: d4a8625d562b48bc89d2e411bacae15fc955cf71
Parents: 3ce97c9
Author: Vineet Garg <vg...@apache.org>
Authored: Tue Aug 7 12:26:31 2018 -0700
Committer: Vineet Garg <vg...@apache.org>
Committed: Tue Aug 7 12:26:31 2018 -0700
----------------------------------------------------------------------
.../org/apache/hadoop/hive/conf/HiveConf.java | 2 +-
.../queries/clientpositive/subquery_scalar.q | 3 -
.../clientpositive/llap/subquery_scalar.q.out | 117 ++--
.../clientpositive/perf/spark/query44.q.out | 325 +++++------
.../clientpositive/perf/spark/query54.q.out | 478 ++++++++--------
.../clientpositive/perf/tez/query44.q.out | 170 +++---
.../clientpositive/perf/tez/query54.q.out | 558 +++++++++----------
.../clientpositive/spark/subquery_scalar.q.out | 129 ++---
8 files changed, 808 insertions(+), 974 deletions(-)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/hive/blob/d4a8625d/common/src/java/org/apache/hadoop/hive/conf/HiveConf.java
----------------------------------------------------------------------
diff --git a/common/src/java/org/apache/hadoop/hive/conf/HiveConf.java b/common/src/java/org/apache/hadoop/hive/conf/HiveConf.java
index e251920..5bdcac8 100644
--- a/common/src/java/org/apache/hadoop/hive/conf/HiveConf.java
+++ b/common/src/java/org/apache/hadoop/hive/conf/HiveConf.java
@@ -2247,7 +2247,7 @@ public class HiveConf extends Configuration {
HIVE_COMBINE_EQUIVALENT_WORK_OPTIMIZATION("hive.combine.equivalent.work.optimization", true, "Whether to " +
"combine equivalent work objects during physical optimization.\n This optimization looks for equivalent " +
"work objects and combines them if they meet certain preconditions. Spark only."),
- HIVE_REMOVE_SQ_COUNT_CHECK("hive.optimize.remove.sq_count_check", false,
+ HIVE_REMOVE_SQ_COUNT_CHECK("hive.optimize.remove.sq_count_check", true,
"Whether to remove an extra join with sq_count_check for scalar subqueries "
+ "with constant group by keys."),
http://git-wip-us.apache.org/repos/asf/hive/blob/d4a8625d/ql/src/test/queries/clientpositive/subquery_scalar.q
----------------------------------------------------------------------
diff --git a/ql/src/test/queries/clientpositive/subquery_scalar.q b/ql/src/test/queries/clientpositive/subquery_scalar.q
index 50b8ece..a7322f5 100644
--- a/ql/src/test/queries/clientpositive/subquery_scalar.q
+++ b/ql/src/test/queries/clientpositive/subquery_scalar.q
@@ -252,12 +252,9 @@ drop table t_n11;
drop table tempty_n0;
-- following queries shouldn't have a join with sq_count_check
-set hive.optimize.remove.sq_count_check = true;
explain select key, count(*) from src group by key having count(*) >
(select count(*) from src s1 group by 4);
explain select key, count(*) from src group by key having count(*) >
(select count(*) from src s1 where s1.key = '90' group by s1.key );
-set hive.optimize.remove.sq_count_check = false;
-
http://git-wip-us.apache.org/repos/asf/hive/blob/d4a8625d/ql/src/test/results/clientpositive/llap/subquery_scalar.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/subquery_scalar.q.out b/ql/src/test/results/clientpositive/llap/subquery_scalar.q.out
index f7c8ec7..4423aec 100644
--- a/ql/src/test/results/clientpositive/llap/subquery_scalar.q.out
+++ b/ql/src/test/results/clientpositive/llap/subquery_scalar.q.out
@@ -445,8 +445,8 @@ POSTHOOK: type: QUERY
POSTHOOK: Input: default@part
POSTHOOK: Input: default@part_null_n0
#### A masked pattern was here ####
-Warning: Shuffle Join MERGEJOIN[32][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product
-Warning: Shuffle Join MERGEJOIN[33][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 3' is a cross product
+Warning: Shuffle Join MERGEJOIN[33][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product
+Warning: Shuffle Join MERGEJOIN[34][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 3' is a cross product
PREHOOK: query: explain select * from part where (select i from tnull_n0 limit 1) is null
PREHOOK: type: QUERY
POSTHOOK: query: explain select * from part where (select i from tnull_n0 limit 1) is null
@@ -542,20 +542,24 @@ STAGE PLANS:
1
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col10
Statistics: Num rows: 26 Data size: 16198 Basic stats: COMPLETE Column stats: COMPLETE
- Filter Operator
- predicate: _col10 is null (type: boolean)
- Statistics: Num rows: 1 Data size: 623 Basic stats: COMPLETE Column stats: COMPLETE
- Select Operator
- expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8
- Statistics: Num rows: 1 Data size: 619 Basic stats: COMPLETE Column stats: COMPLETE
- File Output Operator
- compressed: false
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string), _col10 (type: int)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9
+ Statistics: Num rows: 26 Data size: 16198 Basic stats: COMPLETE Column stats: COMPLETE
+ Filter Operator
+ predicate: _col9 is null (type: boolean)
+ Statistics: Num rows: 1 Data size: 623 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8
Statistics: Num rows: 1 Data size: 619 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
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 619 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
Reducer 5
Execution mode: vectorized, llap
Reduce Operator Tree:
@@ -608,8 +612,8 @@ STAGE PLANS:
Processor Tree:
ListSink
-Warning: Shuffle Join MERGEJOIN[32][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product
-Warning: Shuffle Join MERGEJOIN[33][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 3' is a cross product
+Warning: Shuffle Join MERGEJOIN[33][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product
+Warning: Shuffle Join MERGEJOIN[34][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 3' is a cross product
PREHOOK: query: select * from part where (select i from tnull_n0 limit 1) is null
PREHOOK: type: QUERY
PREHOOK: Input: default@part
@@ -2395,8 +2399,8 @@ POSTHOOK: Input: default@part
85768 almond antique chartreuse lavender yellow Manufacturer#1 Brand#12 LARGE BRUSHED STEEL 34 SM BAG 1753.76 refull
86428 almond aquamarine burnished black steel Manufacturer#1 Brand#12 STANDARD ANODIZED STEEL 28 WRAP BAG 1414.42 arefully
90681 almond antique chartreuse khaki white Manufacturer#3 Brand#31 MEDIUM BURNISHED TIN 17 SM CASE 1671.68 are slyly after the sl
-Warning: Shuffle Join MERGEJOIN[47][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product
-Warning: Shuffle Join MERGEJOIN[48][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 4' is a cross product
+Warning: Shuffle Join MERGEJOIN[30][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product
+Warning: Shuffle Join MERGEJOIN[31][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 4' is a cross product
PREHOOK: query: explain select key, count(*) from src where value <> (select max(value) from src) group by key having count(*) > (select count(*) from src s1 where s1.key = '90' group by s1.key )
PREHOOK: type: QUERY
POSTHOOK: query: explain select key, count(*) from src where value <> (select max(value) from src) group by key having count(*) > (select count(*) from src s1 where s1.key = '90' group by s1.key )
@@ -2410,13 +2414,11 @@ STAGE PLANS:
Tez
#### A masked pattern was here ####
Edges:
- Reducer 10 <- Map 7 (SIMPLE_EDGE)
Reducer 2 <- Map 1 (XPROD_EDGE), Reducer 6 (XPROD_EDGE)
Reducer 3 <- Reducer 2 (SIMPLE_EDGE)
- Reducer 4 <- Reducer 10 (XPROD_EDGE), Reducer 3 (XPROD_EDGE), Reducer 9 (XPROD_EDGE)
+ Reducer 4 <- Reducer 3 (XPROD_EDGE), Reducer 8 (XPROD_EDGE)
Reducer 6 <- Map 5 (CUSTOM_SIMPLE_EDGE)
Reducer 8 <- Map 7 (SIMPLE_EDGE)
- Reducer 9 <- Reducer 8 (CUSTOM_SIMPLE_EDGE)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -2466,16 +2468,6 @@ STAGE PLANS:
Select Operator
Statistics: Num rows: 2 Data size: 174 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
- keys: '90' (type: string)
- mode: hash
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 86 Basic stats: COMPLETE Column stats: COMPLETE
- Reduce Output Operator
- key expressions: _col0 (type: string)
- sort order: +
- Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 1 Data size: 86 Basic stats: COMPLETE Column stats: COMPLETE
- Group By Operator
aggregations: count()
keys: '90' (type: string)
mode: hash
@@ -2489,23 +2481,6 @@ STAGE PLANS:
value expressions: _col1 (type: bigint)
Execution mode: vectorized, llap
LLAP IO: no inputs
- Reducer 10
- Execution mode: vectorized, llap
- Reduce Operator Tree:
- Group By Operator
- aggregations: count(VALUE._col0)
- keys: KEY._col0 (type: string)
- mode: mergepartial
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: COMPLETE
- Select Operator
- expressions: _col1 (type: bigint)
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
- Reduce Output Operator
- sort order:
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
- value expressions: _col0 (type: bigint)
Reducer 2
Execution mode: llap
Reduce Operator Tree:
@@ -2553,13 +2528,11 @@ STAGE PLANS:
Merge Join Operator
condition map:
Inner Join 0 to 1
- Inner Join 0 to 2
keys:
0
1
- 2
- outputColumnNames: _col0, _col1, _col3
- residual filter predicates: {(_col1 > _col3)}
+ outputColumnNames: _col0, _col1, _col2
+ residual filter predicates: {(_col1 > _col2)}
Statistics: Num rows: 83 Data size: 8549 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: string), _col1 (type: bigint)
@@ -2588,37 +2561,19 @@ STAGE PLANS:
Execution mode: vectorized, llap
Reduce Operator Tree:
Group By Operator
+ aggregations: count(VALUE._col0)
keys: KEY._col0 (type: string)
mode: mergepartial
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 86 Basic stats: COMPLETE Column stats: COMPLETE
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
- Statistics: Num rows: 1 Data size: 86 Basic stats: COMPLETE Column stats: COMPLETE
- Group By Operator
- aggregations: count()
- mode: hash
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
- Reduce Output Operator
- sort order:
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
- value expressions: _col0 (type: bigint)
- Reducer 9
- Execution mode: vectorized, llap
- Reduce Operator Tree:
- Group By Operator
- aggregations: count(VALUE._col0)
- mode: mergepartial
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
- Filter Operator
- predicate: (sq_count_check(_col0) <= 1) (type: boolean)
+ expressions: _col1 (type: bigint)
+ outputColumnNames: _col0
Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
- Select Operator
+ Reduce Output Operator
+ sort order:
Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
- Reduce Output Operator
- sort order:
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col0 (type: bigint)
Stage: Stage-0
Fetch Operator
@@ -2626,8 +2581,8 @@ STAGE PLANS:
Processor Tree:
ListSink
-Warning: Shuffle Join MERGEJOIN[47][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product
-Warning: Shuffle Join MERGEJOIN[48][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 4' is a cross product
+Warning: Shuffle Join MERGEJOIN[30][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product
+Warning: Shuffle Join MERGEJOIN[31][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 4' is a cross product
PREHOOK: query: select key, count(*) from src where value <> (select max(value) from src) group by key having count(*) > (select count(*) from src s1 where s1.key = '90' group by s1.key )
PREHOOK: type: QUERY
PREHOOK: Input: default@src
http://git-wip-us.apache.org/repos/asf/hive/blob/d4a8625d/ql/src/test/results/clientpositive/perf/spark/query44.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/perf/spark/query44.q.out b/ql/src/test/results/clientpositive/perf/spark/query44.q.out
index 6ba55e9..6410815 100644
--- a/ql/src/test/results/clientpositive/perf/spark/query44.q.out
+++ b/ql/src/test/results/clientpositive/perf/spark/query44.q.out
@@ -1,5 +1,5 @@
-Warning: Shuffle Join JOIN[36][tables = [$hdt$_2, $hdt$_3, $hdt$_1]] in Work 'Reducer 8' is a cross product
-Warning: Shuffle Join JOIN[81][tables = [$hdt$_4, $hdt$_5, $hdt$_3]] in Work 'Reducer 19' is a cross product
+Warning: Shuffle Join JOIN[20][tables = [$hdt$_1, $hdt$_2]] in Work 'Reducer 7' is a cross product
+Warning: Shuffle Join JOIN[49][tables = [$hdt$_3, $hdt$_4]] in Work 'Reducer 15' is a cross product
PREHOOK: query: explain
select asceding.rnk, i1.i_product_name best_performing, i2.i_product_name worst_performing
from(select *
@@ -76,20 +76,18 @@ STAGE PLANS:
Stage: Stage-1
Spark
Edges:
- Reducer 11 <- Map 10 (GROUP, 100)
- Reducer 13 <- Map 12 (GROUP, 199)
- Reducer 15 <- Map 14 (PARTITION-LEVEL SORT, 1009), Reducer 20 (PARTITION-LEVEL SORT, 1009)
- Reducer 17 <- Map 16 (GROUP, 100)
- Reducer 18 <- Reducer 17 (GROUP, 1)
- Reducer 19 <- Reducer 18 (PARTITION-LEVEL SORT, 1), Reducer 22 (PARTITION-LEVEL SORT, 1), Reducer 24 (PARTITION-LEVEL SORT, 1)
- Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 1009), Reducer 9 (PARTITION-LEVEL SORT, 1009)
- Reducer 20 <- Reducer 19 (PARTITION-LEVEL SORT, 1009)
- Reducer 22 <- Map 10 (GROUP, 100)
- Reducer 24 <- Map 12 (GROUP, 199)
- Reducer 3 <- Reducer 15 (PARTITION-LEVEL SORT, 1009), Reducer 2 (PARTITION-LEVEL SORT, 1009)
+ Reducer 10 <- Map 17 (GROUP, 100)
+ Reducer 12 <- Map 11 (PARTITION-LEVEL SORT, 1009), Reducer 16 (PARTITION-LEVEL SORT, 1009)
+ Reducer 14 <- Map 13 (GROUP, 199)
+ Reducer 15 <- Reducer 14 (PARTITION-LEVEL SORT, 1), Reducer 18 (PARTITION-LEVEL SORT, 1)
+ Reducer 16 <- Reducer 15 (PARTITION-LEVEL SORT, 1009)
+ Reducer 18 <- Map 17 (GROUP, 100)
+ Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 1009), Reducer 8 (PARTITION-LEVEL SORT, 1009)
+ Reducer 3 <- Reducer 12 (PARTITION-LEVEL SORT, 1009), Reducer 2 (PARTITION-LEVEL SORT, 1009)
Reducer 4 <- Reducer 3 (SORT, 1)
- Reducer 8 <- Reducer 11 (PARTITION-LEVEL SORT, 1), Reducer 13 (PARTITION-LEVEL SORT, 1), Reducer 18 (PARTITION-LEVEL SORT, 1)
- Reducer 9 <- Reducer 8 (PARTITION-LEVEL SORT, 1009)
+ Reducer 6 <- Map 13 (GROUP, 199)
+ Reducer 7 <- Reducer 10 (PARTITION-LEVEL SORT, 1), Reducer 6 (PARTITION-LEVEL SORT, 1)
+ Reducer 8 <- Reducer 7 (PARTITION-LEVEL SORT, 1009)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -112,33 +110,27 @@ STAGE PLANS:
Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: string)
Execution mode: vectorized
- Map 10
+ Map 11
Map Operator Tree:
TableScan
- alias: store_sales
- filterExpr: ((ss_store_sk = 410) and ss_hdemo_sk is null) (type: boolean)
- Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE
+ alias: i2
+ filterExpr: i_item_sk is not null (type: boolean)
+ Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: ((ss_store_sk = 410) and ss_hdemo_sk is null) (type: boolean)
- Statistics: Num rows: 143998908 Data size: 12703625455 Basic stats: COMPLETE Column stats: NONE
+ predicate: i_item_sk is not null (type: boolean)
+ Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE
Select Operator
- expressions: ss_net_profit (type: decimal(7,2))
- outputColumnNames: _col1
- Statistics: Num rows: 143998908 Data size: 12703625455 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- aggregations: sum(_col1), count(_col1)
- keys: 410 (type: int)
- mode: hash
- outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 143998908 Data size: 12703625455 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: int)
- sort order: +
- Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 143998908 Data size: 12703625455 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col1 (type: decimal(17,2)), _col2 (type: bigint)
+ expressions: i_item_sk (type: int), i_product_name (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: int)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: int)
+ Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: string)
Execution mode: vectorized
- Map 12
+ Map 13
Map Operator Tree:
TableScan
alias: ss1
@@ -164,27 +156,7 @@ STAGE PLANS:
Statistics: Num rows: 287997817 Data size: 25407250999 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: decimal(17,2)), _col2 (type: bigint)
Execution mode: vectorized
- Map 14
- Map Operator Tree:
- TableScan
- alias: i2
- filterExpr: i_item_sk is not null (type: boolean)
- Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: i_item_sk is not null (type: boolean)
- Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: i_item_sk (type: int), i_product_name (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: int)
- sort order: +
- Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col1 (type: string)
- Execution mode: vectorized
- Map 16
+ Map 17
Map Operator Tree:
TableScan
alias: store_sales
@@ -194,19 +166,23 @@ STAGE PLANS:
predicate: ((ss_store_sk = 410) and ss_hdemo_sk is null) (type: boolean)
Statistics: Num rows: 143998908 Data size: 12703625455 Basic stats: COMPLETE Column stats: NONE
Select Operator
+ expressions: ss_net_profit (type: decimal(7,2))
+ outputColumnNames: _col1
Statistics: Num rows: 143998908 Data size: 12703625455 Basic stats: COMPLETE Column stats: NONE
Group By Operator
+ aggregations: sum(_col1), count(_col1)
keys: 410 (type: int)
mode: hash
- outputColumnNames: _col0
+ outputColumnNames: _col0, _col1, _col2
Statistics: Num rows: 143998908 Data size: 12703625455 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
Map-reduce partition columns: _col0 (type: int)
Statistics: Num rows: 143998908 Data size: 12703625455 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: decimal(17,2)), _col2 (type: bigint)
Execution mode: vectorized
- Reducer 11
+ Reducer 10
Execution mode: vectorized
Reduce Operator Tree:
Group By Operator
@@ -223,24 +199,7 @@ STAGE PLANS:
sort order:
Statistics: Num rows: 71999454 Data size: 6351812727 Basic stats: COMPLETE Column stats: NONE
value expressions: _col0 (type: decimal(37,22))
- Reducer 13
- Execution mode: vectorized
- Reduce Operator Tree:
- Group By Operator
- aggregations: sum(VALUE._col0), count(VALUE._col1)
- keys: KEY._col0 (type: int)
- mode: mergepartial
- outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 143998908 Data size: 12703625455 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col0 (type: int), (_col1 / _col2) (type: decimal(37,22))
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 143998908 Data size: 12703625455 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- sort order:
- Statistics: Num rows: 143998908 Data size: 12703625455 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col0 (type: int), _col1 (type: decimal(37,22))
- Reducer 15
+ Reducer 12
Reduce Operator Tree:
Join Operator
condition map:
@@ -249,128 +208,92 @@ STAGE PLANS:
0 _col0 (type: int)
1 _col0 (type: int)
outputColumnNames: _col1, _col3
- Statistics: Num rows: 1267180808338276 Data size: 234986744609712256 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1267180808338276 Data size: 224849298143006048 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col3 (type: int)
sort order: +
Map-reduce partition columns: _col3 (type: int)
- Statistics: Num rows: 1267180808338276 Data size: 234986744609712256 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1267180808338276 Data size: 224849298143006048 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: string)
- Reducer 17
+ Reducer 14
Execution mode: vectorized
Reduce Operator Tree:
Group By Operator
+ aggregations: sum(VALUE._col0), count(VALUE._col1)
keys: KEY._col0 (type: int)
mode: mergepartial
- outputColumnNames: _col0
- Statistics: Num rows: 71999454 Data size: 6351812727 Basic stats: COMPLETE Column stats: NONE
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 143998908 Data size: 12703625455 Basic stats: COMPLETE Column stats: NONE
Select Operator
- Statistics: Num rows: 71999454 Data size: 6351812727 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- aggregations: count()
- mode: hash
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- sort order:
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col0 (type: bigint)
- Reducer 18
- Execution mode: vectorized
- Reduce Operator Tree:
- Group By Operator
- aggregations: count(VALUE._col0)
- mode: mergepartial
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: (sq_count_check(_col0) <= 1) (type: boolean)
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- sort order:
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
- Reducer 19
+ expressions: _col0 (type: int), (_col1 / _col2) (type: decimal(37,22))
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 143998908 Data size: 12703625455 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 143998908 Data size: 12703625455 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: int), _col1 (type: decimal(37,22))
+ Reducer 15
Reduce Operator Tree:
Join Operator
condition map:
Inner Join 0 to 1
- Inner Join 0 to 2
keys:
0
1
- 2
- outputColumnNames: _col1, _col2, _col3
- Statistics: Num rows: 10367842752596232 Data size: 1922618777862369774 Basic stats: COMPLETE Column stats: NONE
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 10367842752596232 Data size: 1839676035841599918 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: (_col3 > (0.9 * _col1)) (type: boolean)
- Statistics: Num rows: 3455947584198744 Data size: 640872925954123264 Basic stats: COMPLETE Column stats: NONE
+ predicate: (_col1 > (0.9 * _col2)) (type: boolean)
+ Statistics: Num rows: 3455947584198744 Data size: 613225345280533248 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
- key expressions: 0 (type: int), _col3 (type: decimal(37,22))
+ key expressions: 0 (type: int), _col1 (type: decimal(37,22))
sort order: +-
Map-reduce partition columns: 0 (type: int)
- Statistics: Num rows: 3455947584198744 Data size: 640872925954123264 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3455947584198744 Data size: 613225345280533248 Basic stats: COMPLETE Column stats: NONE
TopN Hash Memory Usage: 0.1
- value expressions: _col2 (type: int)
- Reducer 2
- Reduce Operator Tree:
- Join Operator
- condition map:
- Inner Join 0 to 1
- keys:
- 0 _col0 (type: int)
- 1 _col0 (type: int)
- outputColumnNames: _col1, _col3
- Statistics: Num rows: 1267180808338276 Data size: 234986744609712256 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col3 (type: int)
- sort order: +
- Map-reduce partition columns: _col3 (type: int)
- Statistics: Num rows: 1267180808338276 Data size: 234986744609712256 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col1 (type: string)
- Reducer 20
+ value expressions: _col0 (type: int)
+ Reducer 16
Execution mode: vectorized
Reduce Operator Tree:
Select Operator
- expressions: VALUE._col2 (type: int), KEY.reducesinkkey1 (type: decimal(37,22))
- outputColumnNames: _col2, _col3
- Statistics: Num rows: 3455947584198744 Data size: 640872925954123264 Basic stats: COMPLETE Column stats: NONE
+ expressions: VALUE._col0 (type: int), KEY.reducesinkkey1 (type: decimal(37,22))
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 3455947584198744 Data size: 613225345280533248 Basic stats: COMPLETE Column stats: NONE
PTF Operator
Function definitions:
Input definition
input alias: ptf_0
- output shape: _col2: int, _col3: decimal(37,22)
+ output shape: _col0: int, _col1: decimal(37,22)
type: WINDOWING
Windowing table definition
input alias: ptf_1
name: windowingtablefunction
- order by: _col3 DESC NULLS LAST
+ order by: _col1 DESC NULLS LAST
partition by: 0
raw input shape:
window functions:
window function definition
alias: rank_window_0
- arguments: _col3
+ arguments: _col1
name: rank
window function: GenericUDAFRankEvaluator
window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX)
isPivotResult: true
- Statistics: Num rows: 3455947584198744 Data size: 640872925954123264 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3455947584198744 Data size: 613225345280533248 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: ((rank_window_0 < 11) and _col2 is not null) (type: boolean)
- Statistics: Num rows: 1151982528066248 Data size: 213624308651374400 Basic stats: COMPLETE Column stats: NONE
+ predicate: ((rank_window_0 < 11) and _col0 is not null) (type: boolean)
+ Statistics: Num rows: 1151982528066248 Data size: 204408448426844416 Basic stats: COMPLETE Column stats: NONE
Select Operator
- expressions: _col2 (type: int), rank_window_0 (type: int)
+ expressions: _col0 (type: int), rank_window_0 (type: int)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1151982528066248 Data size: 213624308651374400 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1151982528066248 Data size: 204408448426844416 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 1151982528066248 Data size: 213624308651374400 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1151982528066248 Data size: 204408448426844416 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: int)
- Reducer 22
+ Reducer 18
Execution mode: vectorized
Reduce Operator Tree:
Group By Operator
@@ -387,23 +310,22 @@ STAGE PLANS:
sort order:
Statistics: Num rows: 71999454 Data size: 6351812727 Basic stats: COMPLETE Column stats: NONE
value expressions: _col0 (type: decimal(37,22))
- Reducer 24
- Execution mode: vectorized
+ Reducer 2
Reduce Operator Tree:
- Group By Operator
- aggregations: sum(VALUE._col0), count(VALUE._col1)
- keys: KEY._col0 (type: int)
- mode: mergepartial
- outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 143998908 Data size: 12703625455 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col0 (type: int), (_col1 / _col2) (type: decimal(37,22))
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 143998908 Data size: 12703625455 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- sort order:
- Statistics: Num rows: 143998908 Data size: 12703625455 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col0 (type: int), _col1 (type: decimal(37,22))
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col0 (type: int)
+ 1 _col0 (type: int)
+ outputColumnNames: _col1, _col3
+ Statistics: Num rows: 1267180808338276 Data size: 224849298143006048 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col3 (type: int)
+ sort order: +
+ Map-reduce partition columns: _col3 (type: int)
+ Statistics: Num rows: 1267180808338276 Data size: 224849298143006048 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: string)
Reducer 3
Reduce Operator Tree:
Join Operator
@@ -413,15 +335,15 @@ STAGE PLANS:
0 _col3 (type: int)
1 _col3 (type: int)
outputColumnNames: _col1, _col3, _col5
- Statistics: Num rows: 1393898919384048 Data size: 258485424673204064 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1393898919384048 Data size: 247334233318131680 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: _col3 (type: int), _col1 (type: string), _col5 (type: string)
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 1393898919384048 Data size: 258485424673204064 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1393898919384048 Data size: 247334233318131680 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
- Statistics: Num rows: 1393898919384048 Data size: 258485424673204064 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1393898919384048 Data size: 247334233318131680 Basic stats: COMPLETE Column stats: NONE
TopN Hash Memory Usage: 0.1
value expressions: _col1 (type: string), _col2 (type: string)
Reducer 4
@@ -430,79 +352,94 @@ STAGE PLANS:
Select Operator
expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: string), VALUE._col1 (type: string)
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 1393898919384048 Data size: 258485424673204064 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1393898919384048 Data size: 247334233318131680 Basic stats: COMPLETE Column stats: NONE
Limit
Number of rows: 100
- Statistics: Num rows: 100 Data size: 18500 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 100 Data size: 17700 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 100 Data size: 18500 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 100 Data size: 17700 Basic stats: COMPLETE Column stats: NONE
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
- Reducer 8
+ Reducer 6
+ Execution mode: vectorized
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: sum(VALUE._col0), count(VALUE._col1)
+ keys: KEY._col0 (type: int)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 143998908 Data size: 12703625455 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: int), (_col1 / _col2) (type: decimal(37,22))
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 143998908 Data size: 12703625455 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 143998908 Data size: 12703625455 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: int), _col1 (type: decimal(37,22))
+ Reducer 7
Reduce Operator Tree:
Join Operator
condition map:
Inner Join 0 to 1
- Inner Join 0 to 2
keys:
0
1
- 2
- outputColumnNames: _col1, _col2, _col3
- Statistics: Num rows: 10367842752596232 Data size: 1922618777862369774 Basic stats: COMPLETE Column stats: NONE
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 10367842752596232 Data size: 1839676035841599918 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: (_col3 > (0.9 * _col1)) (type: boolean)
- Statistics: Num rows: 3455947584198744 Data size: 640872925954123264 Basic stats: COMPLETE Column stats: NONE
+ predicate: (_col1 > (0.9 * _col2)) (type: boolean)
+ Statistics: Num rows: 3455947584198744 Data size: 613225345280533248 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
- key expressions: 0 (type: int), _col3 (type: decimal(37,22))
+ key expressions: 0 (type: int), _col1 (type: decimal(37,22))
sort order: ++
Map-reduce partition columns: 0 (type: int)
- Statistics: Num rows: 3455947584198744 Data size: 640872925954123264 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3455947584198744 Data size: 613225345280533248 Basic stats: COMPLETE Column stats: NONE
TopN Hash Memory Usage: 0.1
- value expressions: _col2 (type: int)
- Reducer 9
+ value expressions: _col0 (type: int)
+ Reducer 8
Execution mode: vectorized
Reduce Operator Tree:
Select Operator
- expressions: VALUE._col2 (type: int), KEY.reducesinkkey1 (type: decimal(37,22))
- outputColumnNames: _col2, _col3
- Statistics: Num rows: 3455947584198744 Data size: 640872925954123264 Basic stats: COMPLETE Column stats: NONE
+ expressions: VALUE._col0 (type: int), KEY.reducesinkkey1 (type: decimal(37,22))
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 3455947584198744 Data size: 613225345280533248 Basic stats: COMPLETE Column stats: NONE
PTF Operator
Function definitions:
Input definition
input alias: ptf_0
- output shape: _col2: int, _col3: decimal(37,22)
+ output shape: _col0: int, _col1: decimal(37,22)
type: WINDOWING
Windowing table definition
input alias: ptf_1
name: windowingtablefunction
- order by: _col3 ASC NULLS FIRST
+ order by: _col1 ASC NULLS FIRST
partition by: 0
raw input shape:
window functions:
window function definition
alias: rank_window_0
- arguments: _col3
+ arguments: _col1
name: rank
window function: GenericUDAFRankEvaluator
window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX)
isPivotResult: true
- Statistics: Num rows: 3455947584198744 Data size: 640872925954123264 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3455947584198744 Data size: 613225345280533248 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: ((rank_window_0 < 11) and _col2 is not null) (type: boolean)
- Statistics: Num rows: 1151982528066248 Data size: 213624308651374400 Basic stats: COMPLETE Column stats: NONE
+ predicate: ((rank_window_0 < 11) and _col0 is not null) (type: boolean)
+ Statistics: Num rows: 1151982528066248 Data size: 204408448426844416 Basic stats: COMPLETE Column stats: NONE
Select Operator
- expressions: _col2 (type: int), rank_window_0 (type: int)
+ expressions: _col0 (type: int), rank_window_0 (type: int)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1151982528066248 Data size: 213624308651374400 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1151982528066248 Data size: 204408448426844416 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 1151982528066248 Data size: 213624308651374400 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1151982528066248 Data size: 204408448426844416 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: int)
Stage: Stage-0
http://git-wip-us.apache.org/repos/asf/hive/blob/d4a8625d/ql/src/test/results/clientpositive/perf/spark/query54.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/perf/spark/query54.q.out b/ql/src/test/results/clientpositive/perf/spark/query54.q.out
index 3d2c4da..241d6d8 100644
--- a/ql/src/test/results/clientpositive/perf/spark/query54.q.out
+++ b/ql/src/test/results/clientpositive/perf/spark/query54.q.out
@@ -1,6 +1,6 @@
-Warning: Shuffle Join JOIN[111][tables = [$hdt$_1, $hdt$_2]] in Work 'Reducer 3' is a cross product
-Warning: Shuffle Join JOIN[107][tables = [$hdt$_0, $hdt$_1, $hdt$_2, $hdt$_3, $hdt$_4]] in Work 'Reducer 14' is a cross product
-Warning: Shuffle Join JOIN[114][tables = [$hdt$_1, $hdt$_2, $hdt$_0]] in Work 'Reducer 4' is a cross product
+Warning: Shuffle Join JOIN[84][tables = [$hdt$_0, $hdt$_1, $hdt$_2, $hdt$_3, $hdt$_4]] in Work 'Reducer 4' is a cross product
+Warning: Shuffle Join JOIN[115][tables = [$hdt$_0, $hdt$_1]] in Work 'Reducer 5' is a cross product
+Warning: Map Join MAPJOIN[145][bigTable=?] in task 'Stage-1:MAPRED' is a cross product
Warning: Map Join MAPJOIN[144][bigTable=?] in task 'Stage-1:MAPRED' is a cross product
PREHOOK: query: explain
with my_customers as (
@@ -115,18 +115,19 @@ POSTHOOK: type: QUERY
STAGE DEPENDENCIES:
Stage-2 is a root stage
Stage-3 depends on stages: Stage-2
- Stage-1 depends on stages: Stage-3
+ Stage-4 depends on stages: Stage-3
+ Stage-1 depends on stages: Stage-4
Stage-0 depends on stages: Stage-1
STAGE PLANS:
Stage: Stage-2
Spark
Edges:
- Reducer 29 <- Map 28 (GROUP, 2)
- Reducer 30 <- Reducer 29 (GROUP, 1)
+ Reducer 28 <- Map 27 (GROUP, 2)
+ Reducer 29 <- Reducer 28 (GROUP, 1)
#### A masked pattern was here ####
Vertices:
- Map 28
+ Map 27
Map Operator Tree:
TableScan
alias: date_dim
@@ -136,7 +137,7 @@ STAGE PLANS:
predicate: ((d_moy = 3) and (d_year = 1999)) (type: boolean)
Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE
Select Operator
- expressions: (d_month_seq + 1) (type: int)
+ expressions: (d_month_seq + 3) (type: int)
outputColumnNames: _col0
Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE
Group By Operator
@@ -150,7 +151,7 @@ STAGE PLANS:
Map-reduce partition columns: _col0 (type: int)
Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE
Execution mode: vectorized
- Reducer 29
+ Reducer 28
Execution mode: vectorized
Reduce Operator Tree:
Group By Operator
@@ -169,7 +170,7 @@ STAGE PLANS:
sort order:
Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
value expressions: _col0 (type: bigint)
- Reducer 30
+ Reducer 29
Execution mode: vectorized
Local Work:
Map Reduce Local Work
@@ -191,9 +192,79 @@ STAGE PLANS:
Stage: Stage-3
Spark
+ Edges:
+ Reducer 23 <- Map 22 (GROUP, 2)
+ Reducer 24 <- Reducer 23 (GROUP, 1)
#### A masked pattern was here ####
Vertices:
- Map 18
+ Map 22
+ Map Operator Tree:
+ TableScan
+ alias: date_dim
+ filterExpr: ((d_year = 1999) and (d_moy = 3)) (type: boolean)
+ Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: ((d_moy = 3) and (d_year = 1999)) (type: boolean)
+ Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: (d_month_seq + 1) (type: int)
+ outputColumnNames: _col0
+ Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ keys: _col0 (type: int)
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: int)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: int)
+ Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE
+ Execution mode: vectorized
+ Reducer 23
+ Execution mode: vectorized
+ Reduce Operator Tree:
+ Group By Operator
+ keys: KEY._col0 (type: int)
+ mode: mergepartial
+ outputColumnNames: _col0
+ Statistics: Num rows: 9131 Data size: 10217589 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ Statistics: Num rows: 9131 Data size: 10217589 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: count()
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: bigint)
+ Reducer 24
+ Execution mode: vectorized
+ Local Work:
+ Map Reduce Local Work
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: count(VALUE._col0)
+ mode: mergepartial
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (sq_count_check(_col0) <= 1) (type: boolean)
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Spark HashTable Sink Operator
+ keys:
+ 0
+ 1
+
+ Stage: Stage-4
+ Spark
+#### A masked pattern was here ####
+ Vertices:
+ Map 12
Map Operator Tree:
TableScan
alias: store
@@ -217,52 +288,25 @@ STAGE PLANS:
Stage: Stage-1
Spark
Edges:
- Reducer 10 <- Reducer 9 (GROUP, 1)
- Reducer 12 <- Map 11 (PARTITION-LEVEL SORT, 398), Map 15 (PARTITION-LEVEL SORT, 398)
- Reducer 13 <- Reducer 12 (PARTITION-LEVEL SORT, 772), Reducer 17 (PARTITION-LEVEL SORT, 772)
- Reducer 14 <- Reducer 13 (PARTITION-LEVEL SORT, 1), Reducer 32 (PARTITION-LEVEL SORT, 1)
- Reducer 17 <- Map 16 (PARTITION-LEVEL SORT, 654), Reducer 23 (PARTITION-LEVEL SORT, 654)
- Reducer 2 <- Map 1 (GROUP, 2)
- Reducer 20 <- Map 19 (PARTITION-LEVEL SORT, 458), Map 24 (PARTITION-LEVEL SORT, 458), Map 25 (PARTITION-LEVEL SORT, 458)
- Reducer 21 <- Map 26 (PARTITION-LEVEL SORT, 505), Reducer 20 (PARTITION-LEVEL SORT, 505)
- Reducer 22 <- Map 27 (PARTITION-LEVEL SORT, 1009), Reducer 21 (PARTITION-LEVEL SORT, 1009)
- Reducer 23 <- Reducer 22 (GROUP, 610)
- Reducer 3 <- Reducer 10 (PARTITION-LEVEL SORT, 1), Reducer 2 (PARTITION-LEVEL SORT, 1)
- Reducer 32 <- Map 31 (GROUP, 2)
- Reducer 4 <- Reducer 14 (PARTITION-LEVEL SORT, 1), Reducer 3 (PARTITION-LEVEL SORT, 1)
- Reducer 5 <- Reducer 4 (GROUP, 1009)
+ Reducer 11 <- Map 10 (PARTITION-LEVEL SORT, 654), Reducer 17 (PARTITION-LEVEL SORT, 654)
+ Reducer 14 <- Map 13 (PARTITION-LEVEL SORT, 458), Map 18 (PARTITION-LEVEL SORT, 458), Map 19 (PARTITION-LEVEL SORT, 458)
+ Reducer 15 <- Map 20 (PARTITION-LEVEL SORT, 505), Reducer 14 (PARTITION-LEVEL SORT, 505)
+ Reducer 16 <- Map 21 (PARTITION-LEVEL SORT, 1009), Reducer 15 (PARTITION-LEVEL SORT, 1009)
+ Reducer 17 <- Reducer 16 (GROUP, 610)
+ Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 398), Map 9 (PARTITION-LEVEL SORT, 398)
+ Reducer 26 <- Map 25 (GROUP, 2)
+ Reducer 3 <- Reducer 11 (PARTITION-LEVEL SORT, 772), Reducer 2 (PARTITION-LEVEL SORT, 772)
+ Reducer 31 <- Map 30 (GROUP, 2)
+ Reducer 4 <- Reducer 26 (PARTITION-LEVEL SORT, 1), Reducer 3 (PARTITION-LEVEL SORT, 1)
+ Reducer 5 <- Reducer 31 (PARTITION-LEVEL SORT, 1), Reducer 4 (PARTITION-LEVEL SORT, 1)
Reducer 6 <- Reducer 5 (GROUP, 1009)
- Reducer 7 <- Reducer 6 (SORT, 1)
- Reducer 9 <- Map 1 (GROUP, 2)
+ Reducer 7 <- Reducer 6 (GROUP, 1009)
+ Reducer 8 <- Reducer 7 (SORT, 1)
#### A masked pattern was here ####
Vertices:
Map 1
Map Operator Tree:
TableScan
- alias: date_dim
- filterExpr: ((d_year = 1999) and (d_moy = 3)) (type: boolean)
- Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: ((d_moy = 3) and (d_year = 1999)) (type: boolean)
- Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: (d_month_seq + 3) (type: int)
- outputColumnNames: _col0
- Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- keys: _col0 (type: int)
- mode: hash
- outputColumnNames: _col0
- Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: int)
- sort order: +
- Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE
- Execution mode: vectorized
- Map 11
- Map Operator Tree:
- TableScan
alias: store_sales
filterExpr: (ss_customer_sk is not null and ss_sold_date_sk is not null) (type: boolean)
Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE
@@ -280,27 +324,7 @@ STAGE PLANS:
Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: int), _col2 (type: decimal(7,2))
Execution mode: vectorized
- Map 15
- Map Operator Tree:
- TableScan
- alias: date_dim
- filterExpr: d_date_sk is not null (type: boolean)
- Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: d_date_sk is not null (type: boolean)
- Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: d_date_sk (type: int), d_month_seq (type: int)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: int)
- sort order: +
- Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col1 (type: int)
- Execution mode: vectorized
- Map 16
+ Map 10
Map Operator Tree:
TableScan
alias: customer_address
@@ -321,7 +345,7 @@ STAGE PLANS:
1 _col0 (type: string), _col1 (type: string)
outputColumnNames: _col0
input vertices:
- 1 Map 18
+ 1 Map 12
Statistics: Num rows: 44000000 Data size: 44654715780 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: int)
@@ -331,7 +355,7 @@ STAGE PLANS:
Execution mode: vectorized
Local Work:
Map Reduce Local Work
- Map 19
+ Map 13
Map Operator Tree:
TableScan
alias: catalog_sales
@@ -351,7 +375,7 @@ STAGE PLANS:
Statistics: Num rows: 431992504 Data size: 58579807164 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: int), _col2 (type: int)
Execution mode: vectorized
- Map 24
+ Map 18
Map Operator Tree:
TableScan
alias: web_sales
@@ -371,7 +395,7 @@ STAGE PLANS:
Statistics: Num rows: 431992504 Data size: 58579807164 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: int), _col2 (type: int)
Execution mode: vectorized
- Map 25
+ Map 19
Map Operator Tree:
TableScan
alias: date_dim
@@ -390,7 +414,7 @@ STAGE PLANS:
Map-reduce partition columns: _col0 (type: int)
Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE
Execution mode: vectorized
- Map 26
+ Map 20
Map Operator Tree:
TableScan
alias: item
@@ -409,7 +433,7 @@ STAGE PLANS:
Map-reduce partition columns: _col0 (type: int)
Statistics: Num rows: 115500 Data size: 165890114 Basic stats: COMPLETE Column stats: NONE
Execution mode: vectorized
- Map 27
+ Map 21
Map Operator Tree:
TableScan
alias: customer
@@ -429,7 +453,7 @@ STAGE PLANS:
Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: int)
Execution mode: vectorized
- Map 31
+ Map 25
Map Operator Tree:
TableScan
alias: date_dim
@@ -453,83 +477,51 @@ STAGE PLANS:
Map-reduce partition columns: _col0 (type: int)
Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE
Execution mode: vectorized
- Reducer 10
+ Map 30
+ Map Operator Tree:
+ TableScan
+ alias: date_dim
+ filterExpr: ((d_year = 1999) and (d_moy = 3)) (type: boolean)
+ Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: ((d_moy = 3) and (d_year = 1999)) (type: boolean)
+ Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: (d_month_seq + 3) (type: int)
+ outputColumnNames: _col0
+ Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ keys: _col0 (type: int)
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: int)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: int)
+ Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE
Execution mode: vectorized
- Reduce Operator Tree:
- Group By Operator
- aggregations: count(VALUE._col0)
- mode: mergepartial
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: (sq_count_check(_col0) <= 1) (type: boolean)
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- sort order:
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
- Reducer 12
- Reduce Operator Tree:
- Join Operator
- condition map:
- Inner Join 0 to 1
- keys:
- 0 _col0 (type: int)
- 1 _col0 (type: int)
- outputColumnNames: _col1, _col2, _col4
- Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col1 (type: int)
- sort order: +
- Map-reduce partition columns: _col1 (type: int)
- Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col2 (type: decimal(7,2)), _col4 (type: int)
- Reducer 13
- Local Work:
- Map Reduce Local Work
- Reduce Operator Tree:
- Join Operator
- condition map:
- Inner Join 0 to 1
- keys:
- 0 _col1 (type: int)
- 1 _col5 (type: int)
- outputColumnNames: _col2, _col4, _col10
- Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE
- Map Join Operator
- condition map:
- Inner Join 0 to 1
- keys:
- 0
- 1
- outputColumnNames: _col2, _col4, _col10
- input vertices:
- 1 Reducer 30
- Statistics: Num rows: 696954748 Data size: 67758142923 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- sort order:
- Statistics: Num rows: 696954748 Data size: 67758142923 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col2 (type: decimal(7,2)), _col4 (type: int), _col10 (type: int)
- Reducer 14
- Reduce Operator Tree:
- Join Operator
- condition map:
- Left Outer Join 0 to 1
- keys:
- 0
- 1
- outputColumnNames: _col2, _col4, _col10, _col13
- Statistics: Num rows: 6363893803988 Data size: 7746260663496473 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col10 (type: int), _col2 (type: decimal(7,2)), _col4 (type: int), _col13 (type: int)
- outputColumnNames: _col0, _col4, _col11, _col13
- Statistics: Num rows: 6363893803988 Data size: 7746260663496473 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- sort order:
- Statistics: Num rows: 6363893803988 Data size: 7746260663496473 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col0 (type: int), _col4 (type: decimal(7,2)), _col11 (type: int), _col13 (type: int)
- Reducer 17
+ Map 9
+ Map Operator Tree:
+ TableScan
+ alias: date_dim
+ filterExpr: d_date_sk is not null (type: boolean)
+ Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: d_date_sk is not null (type: boolean)
+ Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: d_date_sk (type: int), d_month_seq (type: int)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: int)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: int)
+ Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: int)
+ Execution mode: vectorized
+ Reducer 11
Reduce Operator Tree:
Join Operator
condition map:
@@ -544,19 +536,7 @@ STAGE PLANS:
sort order: +
Map-reduce partition columns: _col5 (type: int)
Statistics: Num rows: 316240138 Data size: 42883351551 Basic stats: COMPLETE Column stats: NONE
- Reducer 2
- Execution mode: vectorized
- Reduce Operator Tree:
- Group By Operator
- keys: KEY._col0 (type: int)
- mode: mergepartial
- outputColumnNames: _col0
- Statistics: Num rows: 9131 Data size: 10217589 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- sort order:
- Statistics: Num rows: 9131 Data size: 10217589 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col0 (type: int)
- Reducer 20
+ Reducer 14
Reduce Operator Tree:
Join Operator
condition map:
@@ -572,7 +552,7 @@ STAGE PLANS:
Map-reduce partition columns: _col2 (type: int)
Statistics: Num rows: 475191764 Data size: 64437789277 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: int)
- Reducer 21
+ Reducer 15
Reduce Operator Tree:
Join Operator
condition map:
@@ -587,7 +567,7 @@ STAGE PLANS:
sort order: +
Map-reduce partition columns: _col1 (type: int)
Statistics: Num rows: 522710951 Data size: 70881569741 Basic stats: COMPLETE Column stats: NONE
- Reducer 22
+ Reducer 16
Reduce Operator Tree:
Join Operator
condition map:
@@ -607,7 +587,7 @@ STAGE PLANS:
sort order: ++
Map-reduce partition columns: _col0 (type: int), _col1 (type: int)
Statistics: Num rows: 574982058 Data size: 77969728405 Basic stats: COMPLETE Column stats: NONE
- Reducer 23
+ Reducer 17
Execution mode: vectorized
Reduce Operator Tree:
Group By Operator
@@ -625,24 +605,61 @@ STAGE PLANS:
Map-reduce partition columns: _col1 (type: int)
Statistics: Num rows: 287491029 Data size: 38984864202 Basic stats: COMPLETE Column stats: NONE
value expressions: _col0 (type: int)
- Reducer 3
+ Reducer 2
Reduce Operator Tree:
Join Operator
condition map:
- Right Outer Join 0 to 1
- filter predicates:
- 0
- 1 {true}
+ Inner Join 0 to 1
keys:
- 0
- 1
+ 0 _col0 (type: int)
+ 1 _col0 (type: int)
+ outputColumnNames: _col1, _col2, _col4
+ Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col1 (type: int)
+ sort order: +
+ Map-reduce partition columns: _col1 (type: int)
+ Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col2 (type: decimal(7,2)), _col4 (type: int)
+ Reducer 26
+ Execution mode: vectorized
+ Reduce Operator Tree:
+ Group By Operator
+ keys: KEY._col0 (type: int)
+ mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 9131 Data size: 10299768 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9131 Data size: 10217589 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
sort order:
- Statistics: Num rows: 9131 Data size: 10299768 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9131 Data size: 10217589 Basic stats: COMPLETE Column stats: NONE
value expressions: _col0 (type: int)
- Reducer 32
+ Reducer 3
+ Local Work:
+ Map Reduce Local Work
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col1 (type: int)
+ 1 _col5 (type: int)
+ outputColumnNames: _col2, _col4, _col10
+ Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0
+ 1
+ outputColumnNames: _col2, _col4, _col10
+ input vertices:
+ 1 Reducer 24
+ Statistics: Num rows: 696954748 Data size: 67758142923 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 696954748 Data size: 67758142923 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col2 (type: decimal(7,2)), _col4 (type: int), _col10 (type: int)
+ Reducer 31
Execution mode: vectorized
Reduce Operator Tree:
Group By Operator
@@ -655,39 +672,69 @@ STAGE PLANS:
Statistics: Num rows: 9131 Data size: 10217589 Basic stats: COMPLETE Column stats: NONE
value expressions: _col0 (type: int)
Reducer 4
+ Local Work:
+ Map Reduce Local Work
Reduce Operator Tree:
Join Operator
condition map:
- Inner Join 0 to 1
+ Left Outer Join 0 to 1
keys:
0
1
- outputColumnNames: _col0, _col2, _col6, _col13, _col15
- Statistics: Num rows: 58108714324214428 Data size: 9223372036854775807 Basic stats: COMPLETE Column stats: NONE
+ outputColumnNames: _col2, _col4, _col10, _col13
+ Statistics: Num rows: 6363893803988 Data size: 7746260663496473 Basic stats: COMPLETE Column stats: NONE
Select Operator
- expressions: _col2 (type: int), _col6 (type: decimal(7,2)), _col13 (type: int), _col15 (type: int), _col0 (type: int)
- outputColumnNames: _col0, _col4, _col11, _col13, _col15
- Statistics: Num rows: 58108714324214428 Data size: 9223372036854775807 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: _col11 BETWEEN _col13 AND _col15 (type: boolean)
- Statistics: Num rows: 6456523813801603 Data size: 1024819115206086144 Basic stats: COMPLETE Column stats: NONE
+ expressions: _col10 (type: int), _col2 (type: decimal(7,2)), _col4 (type: int), _col13 (type: int)
+ outputColumnNames: _col0, _col4, _col11, _col13
+ Statistics: Num rows: 6363893803988 Data size: 7746260663496473 Basic stats: COMPLETE Column stats: NONE
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0
+ 1
+ outputColumnNames: _col0, _col4, _col11, _col13
+ input vertices:
+ 1 Reducer 29
+ Statistics: Num rows: 6363893803988 Data size: 7803535707732365 Basic stats: COMPLETE Column stats: NONE
Select Operator
- expressions: _col0 (type: int), _col4 (type: decimal(7,2))
- outputColumnNames: _col0, _col4
+ expressions: _col0 (type: int), _col4 (type: decimal(7,2)), _col11 (type: int), _col13 (type: int)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 6363893803988 Data size: 7803535707732365 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 6363893803988 Data size: 7803535707732365 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: int), _col1 (type: decimal(7,2)), _col2 (type: int), _col3 (type: int)
+ Reducer 5
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Left Outer Join 0 to 1
+ keys:
+ 0
+ 1
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4
+ Statistics: Num rows: 58108714324214428 Data size: 9223372036854775807 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: _col2 BETWEEN _col3 AND _col4 (type: boolean)
+ Statistics: Num rows: 6456523813801603 Data size: 1024819115206086144 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: decimal(7,2))
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 6456523813801603 Data size: 1024819115206086144 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: sum(_col1)
+ keys: _col0 (type: int)
+ mode: hash
+ outputColumnNames: _col0, _col1
Statistics: Num rows: 6456523813801603 Data size: 1024819115206086144 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- aggregations: sum(_col4)
- keys: _col0 (type: int)
- mode: hash
- outputColumnNames: _col0, _col1
+ Reduce Output Operator
+ key expressions: _col0 (type: int)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: int)
Statistics: Num rows: 6456523813801603 Data size: 1024819115206086144 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: int)
- sort order: +
- Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 6456523813801603 Data size: 1024819115206086144 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col1 (type: decimal(17,2))
- Reducer 5
+ value expressions: _col1 (type: decimal(17,2))
+ Reducer 6
Execution mode: vectorized
Reduce Operator Tree:
Group By Operator
@@ -712,7 +759,7 @@ STAGE PLANS:
Map-reduce partition columns: _col0 (type: int)
Statistics: Num rows: 3228261906900801 Data size: 512409557603043008 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: bigint)
- Reducer 6
+ Reducer 7
Execution mode: vectorized
Reduce Operator Tree:
Group By Operator
@@ -731,7 +778,7 @@ STAGE PLANS:
Statistics: Num rows: 1614130953450400 Data size: 256204778801521408 Basic stats: COMPLETE Column stats: NONE
TopN Hash Memory Usage: 0.1
value expressions: _col2 (type: int)
- Reducer 7
+ Reducer 8
Execution mode: vectorized
Reduce Operator Tree:
Select Operator
@@ -748,25 +795,6 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- Reducer 9
- Execution mode: vectorized
- Reduce Operator Tree:
- Group By Operator
- keys: KEY._col0 (type: int)
- mode: mergepartial
- outputColumnNames: _col0
- Statistics: Num rows: 9131 Data size: 10217589 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- Statistics: Num rows: 9131 Data size: 10217589 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- aggregations: count()
- mode: hash
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- sort order:
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col0 (type: bigint)
Stage: Stage-0
Fetch Operator