You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@hive.apache.org by pr...@apache.org on 2016/08/23 18:46:07 UTC
[36/51] [partial] hive git commit: HIVE-14502: Convert MiniTez tests
to MiniLlap tests (Prasanth Jayachandran reviewed by Siddharth Seth)
http://git-wip-us.apache.org/repos/asf/hive/blob/5f01dc42/ql/src/test/results/clientpositive/llap/count.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/count.q.out b/ql/src/test/results/clientpositive/llap/count.q.out
index e8d5a8a..5c38049 100644
--- a/ql/src/test/results/clientpositive/llap/count.q.out
+++ b/ql/src/test/results/clientpositive/llap/count.q.out
@@ -42,6 +42,7 @@ STAGE DEPENDENCIES:
STAGE PLANS:
Stage: Stage-1
Tez
+#### A masked pattern was here ####
Edges:
Reducer 2 <- Map 1 (SIMPLE_EDGE)
#### A masked pattern was here ####
@@ -68,8 +69,9 @@ STAGE PLANS:
Statistics: Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE
value expressions: _col5 (type: bigint)
Execution mode: llap
+ LLAP IO: no inputs
Reducer 2
- Execution mode: uber
+ Execution mode: llap
Reduce Operator Tree:
Group By Operator
aggregations: count(DISTINCT KEY._col1:0._col0), count(DISTINCT KEY._col1:1._col0), sum(VALUE._col2)
@@ -81,8 +83,8 @@ STAGE PLANS:
compressed: false
Statistics: Num rows: 2 Data size: 39 Basic stats: COMPLETE Column stats: NONE
table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
Stage: Stage-0
@@ -114,6 +116,7 @@ STAGE DEPENDENCIES:
STAGE PLANS:
Stage: Stage-1
Tez
+#### A masked pattern was here ####
Edges:
Reducer 2 <- Map 1 (SIMPLE_EDGE)
#### A masked pattern was here ####
@@ -139,8 +142,9 @@ STAGE PLANS:
Statistics: Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE
value expressions: _col4 (type: bigint), _col5 (type: bigint), _col6 (type: bigint), _col7 (type: bigint), _col8 (type: bigint), _col9 (type: bigint)
Execution mode: llap
+ LLAP IO: no inputs
Reducer 2
- Execution mode: uber
+ Execution mode: llap
Reduce Operator Tree:
Group By Operator
aggregations: count(VALUE._col0), count(VALUE._col1), count(VALUE._col2), count(VALUE._col3), count(VALUE._col4), count(VALUE._col5), count(DISTINCT KEY._col0:0._col0), count(DISTINCT KEY._col0:1._col0), count(DISTINCT KEY._col0:2._col0), count(DISTINCT KEY._col0:3._col0), count(DISTINCT KEY._col0:4._col0, KEY._col0:4._col1), count(DISTINCT KEY._col0:5._col0, KEY._col0:5._col1), count(DISTINCT KEY._col0:6._col0, KEY._col0:6._col1), count(DISTINCT KEY._col0:7._col0, KEY._col0:7._col1), count(DISTINCT KEY._col0:8._col0, KEY._col0:8._col1), count(DISTINCT KEY._col0:9._col0, KEY._col0:9._col1), count(DISTINCT KEY._col0:10._col0, KEY._col0:10._col1, KEY._col0:10._col2), count(DISTINCT KEY._col0:11._col0, KEY._col0:11._col1, KEY._col0:11._col2), count(DISTINCT KEY._col0:12._col0, KEY._col0:12._col1, KEY._col0:12._col2), count(DISTINCT KEY._col0:13._col0, KEY._col0:13._col1, KEY._col0:13._col2), count(DISTINCT KEY._col0:14._col0, KEY._col0:14._col1, KEY._col0:14._col2, KEY.
_col0:14._col3)
@@ -151,8 +155,8 @@ STAGE PLANS:
compressed: false
Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: NONE
table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
Stage: Stage-0
@@ -181,6 +185,7 @@ STAGE DEPENDENCIES:
STAGE PLANS:
Stage: Stage-1
Tez
+#### A masked pattern was here ####
Edges:
Reducer 2 <- Map 1 (SIMPLE_EDGE)
#### A masked pattern was here ####
@@ -201,8 +206,9 @@ STAGE PLANS:
Statistics: Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE
value expressions: d (type: int)
Execution mode: llap
+ LLAP IO: no inputs
Reducer 2
- Execution mode: uber
+ Execution mode: llap
Reduce Operator Tree:
Group By Operator
aggregations: count(DISTINCT KEY._col1:0._col0), count(DISTINCT KEY._col1:1._col0), sum(VALUE._col0)
@@ -214,8 +220,8 @@ STAGE PLANS:
compressed: false
Statistics: Num rows: 2 Data size: 39 Basic stats: COMPLETE Column stats: NONE
table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
Stage: Stage-0
@@ -247,6 +253,7 @@ STAGE DEPENDENCIES:
STAGE PLANS:
Stage: Stage-1
Tez
+#### A masked pattern was here ####
Edges:
Reducer 2 <- Map 1 (SIMPLE_EDGE)
#### A masked pattern was here ####
@@ -265,8 +272,9 @@ STAGE PLANS:
sort order: ++++
Statistics: Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE
Execution mode: llap
+ LLAP IO: no inputs
Reducer 2
- Execution mode: uber
+ Execution mode: llap
Reduce Operator Tree:
Group By Operator
aggregations: count(1), count(), count(KEY._col0:0._col0), count(KEY._col0:1._col0), count(KEY._col0:2._col0), count(KEY._col0:3._col0), count(DISTINCT KEY._col0:0._col0), count(DISTINCT KEY._col0:1._col0), count(DISTINCT KEY._col0:2._col0), count(DISTINCT KEY._col0:3._col0), count(DISTINCT KEY._col0:4._col0, KEY._col0:4._col1), count(DISTINCT KEY._col0:5._col0, KEY._col0:5._col1), count(DISTINCT KEY._col0:6._col0, KEY._col0:6._col1), count(DISTINCT KEY._col0:7._col0, KEY._col0:7._col1), count(DISTINCT KEY._col0:8._col0, KEY._col0:8._col1), count(DISTINCT KEY._col0:9._col0, KEY._col0:9._col1), count(DISTINCT KEY._col0:10._col0, KEY._col0:10._col1, KEY._col0:10._col2), count(DISTINCT KEY._col0:11._col0, KEY._col0:11._col1, KEY._col0:11._col2), count(DISTINCT KEY._col0:12._col0, KEY._col0:12._col1, KEY._col0:12._col2), count(DISTINCT KEY._col0:13._col0, KEY._col0:13._col1, KEY._col0:13._col2), count(DISTINCT KEY._col0:14._col0, KEY._col0:14._col1, KEY._col0:14._col2, K
EY._col0:14._col3)
@@ -277,8 +285,618 @@ STAGE PLANS:
compressed: false
Statistics: Num rows: 1 Data size: 168 Basic stats: COMPLETE Column stats: NONE
table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: select count(1), count(*), count(a), count(b), count(c), count(d), count(distinct a), count(distinct b), count(distinct c), count(distinct d), count(distinct a,b), count(distinct b,c), count(distinct c,d), count(distinct a,d), count(distinct a,c), count(distinct b,d), count(distinct a,b,c), count(distinct b,c,d), count(distinct a,c,d), count(distinct a,b,d), count(distinct a,b,c,d) from abcd
+PREHOOK: type: QUERY
+PREHOOK: Input: default@abcd
+#### A masked pattern was here ####
+POSTHOOK: query: select count(1), count(*), count(a), count(b), count(c), count(d), count(distinct a), count(distinct b), count(distinct c), count(distinct d), count(distinct a,b), count(distinct b,c), count(distinct c,d), count(distinct a,d), count(distinct a,c), count(distinct b,d), count(distinct a,b,c), count(distinct b,c,d), count(distinct a,c,d), count(distinct a,b,d), count(distinct a,b,c,d) from abcd
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@abcd
+#### A masked pattern was here ####
+7 7 6 6 6 7 3 3 6 7 4 5 6 6 5 6 4 5 5 5 4
+PREHOOK: query: --first aggregation with literal. gbinfo was generating wrong expression
+explain select count(1), count(*), count(a), count(b), count(c), count(d), count(distinct a), count(distinct b), count(distinct c), count(distinct d), count(distinct a,b), count(distinct b,c), count(distinct c,d), count(distinct a,d), count(distinct a,c), count(distinct b,d), count(distinct a,b,c), count(distinct b,c,d), count(distinct a,c,d), count(distinct a,b,d), count(distinct a,b,c,d) from abcd
+PREHOOK: type: QUERY
+POSTHOOK: query: --first aggregation with literal. gbinfo was generating wrong expression
+explain select count(1), count(*), count(a), count(b), count(c), count(d), count(distinct a), count(distinct b), count(distinct c), count(distinct d), count(distinct a,b), count(distinct b,c), count(distinct c,d), count(distinct a,d), count(distinct a,c), count(distinct b,d), count(distinct a,b,c), count(distinct b,c,d), count(distinct a,c,d), count(distinct a,b,d), count(distinct a,b,c,d) from abcd
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Tez
+#### A masked pattern was here ####
+ Edges:
+ Reducer 2 <- Map 1 (SIMPLE_EDGE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: abcd
+ Statistics: Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: a (type: int), b (type: int), c (type: int), d (type: int)
+ outputColumnNames: $f1, $f2, $f3, $f4
+ Statistics: Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: count(1), count(), count($f1), count($f2), count($f3), count($f4), count(DISTINCT $f1), count(DISTINCT $f2), count(DISTINCT $f3), count(DISTINCT $f4), count(DISTINCT $f1, $f2), count(DISTINCT $f2, $f3), count(DISTINCT $f3, $f4), count(DISTINCT $f1, $f4), count(DISTINCT $f1, $f3), count(DISTINCT $f2, $f4), count(DISTINCT $f1, $f2, $f3), count(DISTINCT $f2, $f3, $f4), count(DISTINCT $f1, $f3, $f4), count(DISTINCT $f1, $f2, $f4), count(DISTINCT $f1, $f2, $f3, $f4)
+ keys: $f1 (type: int), $f2 (type: int), $f3 (type: int), $f4 (type: int)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24
+ Statistics: Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int), _col3 (type: int)
+ sort order: ++++
+ Statistics: Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col4 (type: bigint), _col5 (type: bigint), _col6 (type: bigint), _col7 (type: bigint), _col8 (type: bigint), _col9 (type: bigint)
+ Execution mode: llap
+ LLAP IO: no inputs
+ Reducer 2
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: count(VALUE._col0), count(VALUE._col1), count(VALUE._col2), count(VALUE._col3), count(VALUE._col4), count(VALUE._col5), count(DISTINCT KEY._col0:0._col0), count(DISTINCT KEY._col0:1._col0), count(DISTINCT KEY._col0:2._col0), count(DISTINCT KEY._col0:3._col0), count(DISTINCT KEY._col0:4._col0, KEY._col0:4._col1), count(DISTINCT KEY._col0:5._col0, KEY._col0:5._col1), count(DISTINCT KEY._col0:6._col0, KEY._col0:6._col1), count(DISTINCT KEY._col0:7._col0, KEY._col0:7._col1), count(DISTINCT KEY._col0:8._col0, KEY._col0:8._col1), count(DISTINCT KEY._col0:9._col0, KEY._col0:9._col1), count(DISTINCT KEY._col0:10._col0, KEY._col0:10._col1, KEY._col0:10._col2), count(DISTINCT KEY._col0:11._col0, KEY._col0:11._col1, KEY._col0:11._col2), count(DISTINCT KEY._col0:12._col0, KEY._col0:12._col1, KEY._col0:12._col2), count(DISTINCT KEY._col0:13._col0, KEY._col0:13._col1, KEY._col0:13._col2), count(DISTINCT KEY._col0:14._col0, KEY._col0:14._col1, KEY._col0:14._col2, KEY.
_col0:14._col3)
+ mode: mergepartial
+ outputColumnNames: $f0, $f1, $f2, $f3, $f4, $f5, $f6, $f7, $f8, $f9, $f10, $f11, $f12, $f13, $f14, $f15, $f16, $f17, $f18, $f19, $f20
+ Statistics: Num rows: 1 Data size: 336 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 336 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
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: select count(1), count(*), count(a), count(b), count(c), count(d), count(distinct a), count(distinct b), count(distinct c), count(distinct d), count(distinct a,b), count(distinct b,c), count(distinct c,d), count(distinct a,d), count(distinct a,c), count(distinct b,d), count(distinct a,b,c), count(distinct b,c,d), count(distinct a,c,d), count(distinct a,b,d), count(distinct a,b,c,d) from abcd
+PREHOOK: type: QUERY
+PREHOOK: Input: default@abcd
+#### A masked pattern was here ####
+POSTHOOK: query: select count(1), count(*), count(a), count(b), count(c), count(d), count(distinct a), count(distinct b), count(distinct c), count(distinct d), count(distinct a,b), count(distinct b,c), count(distinct c,d), count(distinct a,d), count(distinct a,c), count(distinct b,d), count(distinct a,b,c), count(distinct b,c,d), count(distinct a,c,d), count(distinct a,b,d), count(distinct a,b,c,d) from abcd
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@abcd
+#### A masked pattern was here ####
+7 7 6 6 6 7 3 3 6 7 4 5 6 6 5 6 4 5 5 5 4
+PREHOOK: query: explain select count(distinct b) from abcd group by a
+PREHOOK: type: QUERY
+POSTHOOK: query: explain select count(distinct b) from abcd group by a
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Tez
+#### A masked pattern was here ####
+ Edges:
+ Reducer 2 <- Map 1 (SIMPLE_EDGE)
+ Reducer 3 <- Reducer 2 (SIMPLE_EDGE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: abcd
+ Statistics: Num rows: 9 Data size: 78 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: a (type: int), b (type: int)
+ outputColumnNames: a, b
+ Statistics: Num rows: 9 Data size: 78 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: a (type: int), b (type: int)
+ sort order: ++
+ Map-reduce partition columns: a (type: int), b (type: int)
+ Statistics: Num rows: 9 Data size: 78 Basic stats: COMPLETE Column stats: NONE
+ Execution mode: llap
+ LLAP IO: no inputs
+ Reducer 2
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ keys: KEY._col0 (type: int), KEY._col1 (type: int)
+ mode: complete
+ outputColumnNames: a, b
+ Statistics: Num rows: 4 Data size: 34 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: a (type: int)
+ sort order: +
+ Map-reduce partition columns: a (type: int)
+ Statistics: Num rows: 4 Data size: 34 Basic stats: COMPLETE Column stats: NONE
+ value expressions: b (type: int)
+ Reducer 3
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: count(VALUE._col0)
+ keys: KEY._col0 (type: int)
+ mode: complete
+ outputColumnNames: a, $f1
+ Statistics: Num rows: 2 Data size: 17 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: $f1 (type: bigint)
+ outputColumnNames: _o__c0
+ Statistics: Num rows: 2 Data size: 17 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 2 Data size: 17 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
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: select count(distinct b) from abcd group by a
+PREHOOK: type: QUERY
+PREHOOK: Input: default@abcd
+#### A masked pattern was here ####
+POSTHOOK: query: select count(distinct b) from abcd group by a
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@abcd
+#### A masked pattern was here ####
+1
+1
+1
+2
+PREHOOK: query: explain select count(distinct b) from abcd group by b
+PREHOOK: type: QUERY
+POSTHOOK: query: explain select count(distinct b) from abcd group by b
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Tez
+#### A masked pattern was here ####
+ Edges:
+ Reducer 2 <- Map 1 (SIMPLE_EDGE)
+ Reducer 3 <- Reducer 2 (SIMPLE_EDGE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: abcd
+ Statistics: Num rows: 19 Data size: 78 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: b (type: int)
+ outputColumnNames: b
+ Statistics: Num rows: 19 Data size: 78 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: b (type: int)
+ sort order: +
+ Map-reduce partition columns: b (type: int)
+ Statistics: Num rows: 19 Data size: 78 Basic stats: COMPLETE Column stats: NONE
+ Execution mode: llap
+ LLAP IO: no inputs
+ Reducer 2
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ keys: KEY._col0 (type: int)
+ mode: complete
+ outputColumnNames: b
+ Statistics: Num rows: 9 Data size: 36 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: b (type: int)
+ sort order: +
+ Map-reduce partition columns: b (type: int)
+ Statistics: Num rows: 9 Data size: 36 Basic stats: COMPLETE Column stats: NONE
+ Reducer 3
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: count(KEY._col0)
+ keys: KEY._col0 (type: int)
+ mode: complete
+ outputColumnNames: b, $f1
+ Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: $f1 (type: bigint)
+ outputColumnNames: _o__c0
+ Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 4 Data size: 16 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
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: select count(distinct b) from abcd group by b
+PREHOOK: type: QUERY
+PREHOOK: Input: default@abcd
+#### A masked pattern was here ####
+POSTHOOK: query: select count(distinct b) from abcd group by b
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@abcd
+#### A masked pattern was here ####
+0
+1
+1
+1
+PREHOOK: query: explain select count(distinct b) from abcd group by c
+PREHOOK: type: QUERY
+POSTHOOK: query: explain select count(distinct b) from abcd group by c
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Tez
+#### A masked pattern was here ####
+ Edges:
+ Reducer 2 <- Map 1 (SIMPLE_EDGE)
+ Reducer 3 <- Reducer 2 (SIMPLE_EDGE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: abcd
+ Statistics: Num rows: 9 Data size: 78 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: b (type: int), c (type: int)
+ outputColumnNames: b, c
+ Statistics: Num rows: 9 Data size: 78 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: b (type: int), c (type: int)
+ sort order: ++
+ Map-reduce partition columns: b (type: int), c (type: int)
+ Statistics: Num rows: 9 Data size: 78 Basic stats: COMPLETE Column stats: NONE
+ Execution mode: llap
+ LLAP IO: no inputs
+ Reducer 2
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ keys: KEY._col0 (type: int), KEY._col1 (type: int)
+ mode: complete
+ outputColumnNames: b, c
+ Statistics: Num rows: 4 Data size: 34 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: c (type: int)
+ sort order: +
+ Map-reduce partition columns: c (type: int)
+ Statistics: Num rows: 4 Data size: 34 Basic stats: COMPLETE Column stats: NONE
+ value expressions: b (type: int)
+ Reducer 3
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: count(VALUE._col0)
+ keys: KEY._col0 (type: int)
+ mode: complete
+ outputColumnNames: c, $f1
+ Statistics: Num rows: 2 Data size: 17 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: $f1 (type: bigint)
+ outputColumnNames: _o__c0
+ Statistics: Num rows: 2 Data size: 17 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 2 Data size: 17 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
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: select count(distinct b) from abcd group by c
+PREHOOK: type: QUERY
+PREHOOK: Input: default@abcd
+#### A masked pattern was here ####
+POSTHOOK: query: select count(distinct b) from abcd group by c
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@abcd
+#### A masked pattern was here ####
+0
+1
+1
+1
+1
+1
+1
+PREHOOK: query: explain select count(b), count(distinct c) from abcd group by d
+PREHOOK: type: QUERY
+POSTHOOK: query: explain select count(b), count(distinct c) from abcd group by d
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Tez
+#### A masked pattern was here ####
+ Edges:
+ Reducer 2 <- Map 1 (SIMPLE_EDGE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: abcd
+ Statistics: Num rows: 6 Data size: 78 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: b (type: int), c (type: int), d (type: int)
+ outputColumnNames: b, c, d
+ Statistics: Num rows: 6 Data size: 78 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: d (type: int), c (type: int)
+ sort order: ++
+ Map-reduce partition columns: d (type: int)
+ Statistics: Num rows: 6 Data size: 78 Basic stats: COMPLETE Column stats: NONE
+ value expressions: b (type: int)
+ Execution mode: llap
+ LLAP IO: no inputs
+ Reducer 2
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: count(VALUE._col0), count(DISTINCT KEY._col1:0._col0)
+ keys: KEY._col0 (type: int)
+ mode: complete
+ outputColumnNames: d, $f1, $f2
+ Statistics: Num rows: 3 Data size: 39 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: $f1 (type: bigint), $f2 (type: bigint)
+ outputColumnNames: _o__c0, _o__c1
+ Statistics: Num rows: 3 Data size: 39 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 3 Data size: 39 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
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: select count(b), count(distinct c) from abcd group by d
+PREHOOK: type: QUERY
+PREHOOK: Input: default@abcd
+#### A masked pattern was here ####
+POSTHOOK: query: select count(b), count(distinct c) from abcd group by d
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@abcd
+#### A masked pattern was here ####
+0 1
+1 0
+1 1
+1 1
+1 1
+1 1
+1 1
+PREHOOK: query: --non distinct aggregate with same column as group by key
+explain select a, count(distinct b), count(distinct c), sum(d), sum(d+d), sum(d*3), sum(b), sum(c), sum(a), sum(distinct a), sum(distinct b) from abcd group by a
+PREHOOK: type: QUERY
+POSTHOOK: query: --non distinct aggregate with same column as group by key
+explain select a, count(distinct b), count(distinct c), sum(d), sum(d+d), sum(d*3), sum(b), sum(c), sum(a), sum(distinct a), sum(distinct b) from abcd group by a
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Tez
+#### A masked pattern was here ####
+ Edges:
+ Reducer 2 <- Map 1 (SIMPLE_EDGE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: abcd
+ Statistics: Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: a (type: int), b (type: int), c (type: int), d (type: int), (d + d) (type: int), (d * 3) (type: int)
+ outputColumnNames: $f0, $f1, $f2, $f3, $f4, $f5
+ Statistics: Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: $f0 (type: int), $f1 (type: int), $f2 (type: int)
+ sort order: +++
+ Map-reduce partition columns: $f0 (type: int)
+ Statistics: Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE
+ value expressions: $f3 (type: int), $f4 (type: int), $f5 (type: int)
+ Execution mode: llap
+ LLAP IO: no inputs
+ Reducer 2
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: count(DISTINCT KEY._col1:0._col0), count(DISTINCT KEY._col1:1._col0), sum(VALUE._col0), sum(VALUE._col1), sum(VALUE._col2), sum(KEY._col1:0._col0), sum(KEY._col1:1._col0), sum(KEY._col0), sum(DISTINCT KEY._col1:2._col0), sum(DISTINCT KEY._col1:3._col0)
+ keys: KEY._col0 (type: int)
+ mode: complete
+ outputColumnNames: $f0, $f1, $f2, $f3, $f4, $f5, $f6, $f7, $f8, $f9, $f10
+ Statistics: Num rows: 2 Data size: 39 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 2 Data size: 39 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
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: select a, count(distinct b), count(distinct c), sum(d), sum(d+d), sum(d*3), sum(b), sum(c), sum(a), sum(distinct a), sum(distinct b) from abcd group by a
+PREHOOK: type: QUERY
+PREHOOK: Input: default@abcd
+#### A masked pattern was here ####
+POSTHOOK: query: select a, count(distinct b), count(distinct c), sum(d), sum(d+d), sum(d*3), sum(b), sum(c), sum(a), sum(distinct a), sum(distinct b) from abcd group by a
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@abcd
+#### A masked pattern was here ####
+10 2 2 10 20 30 1200 95 30 10 1100
+100 1 1 3 6 9 100 10 100 100 100
+12 1 2 9 18 27 100 155 24 12 100
+NULL 1 1 6 12 18 35 23 NULL NULL 35
+PREHOOK: query: --non distinct aggregate with same column as distinct aggregate
+explain select a, count(distinct b), count(distinct c), sum(d), sum(c) from abcd group by a
+PREHOOK: type: QUERY
+POSTHOOK: query: --non distinct aggregate with same column as distinct aggregate
+explain select a, count(distinct b), count(distinct c), sum(d), sum(c) from abcd group by a
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Tez
+#### A masked pattern was here ####
+ Edges:
+ Reducer 2 <- Map 1 (SIMPLE_EDGE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: abcd
+ Statistics: Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: a (type: int), b (type: int), c (type: int), d (type: int)
+ outputColumnNames: a, b, c, d
+ Statistics: Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: a (type: int), b (type: int), c (type: int)
+ sort order: +++
+ Map-reduce partition columns: a (type: int)
+ Statistics: Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE
+ value expressions: d (type: int)
+ Execution mode: llap
+ LLAP IO: no inputs
+ Reducer 2
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: count(DISTINCT KEY._col1:0._col0), count(DISTINCT KEY._col1:1._col0), sum(VALUE._col0), sum(KEY._col1:1._col0)
+ keys: KEY._col0 (type: int)
+ mode: complete
+ outputColumnNames: a, $f1, $f2, $f3, $f4
+ Statistics: Num rows: 2 Data size: 39 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 2 Data size: 39 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
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: select a, count(distinct b), count(distinct c), sum(d), sum(c) from abcd group by a
+PREHOOK: type: QUERY
+PREHOOK: Input: default@abcd
+#### A masked pattern was here ####
+POSTHOOK: query: select a, count(distinct b), count(distinct c), sum(d), sum(c) from abcd group by a
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@abcd
+#### A masked pattern was here ####
+10 2 2 10 95
+100 1 1 3 10
+12 1 2 9 155
+NULL 1 1 6 23
+PREHOOK: query: --aggregation with literal
+explain select count(1), count(*), count(a), count(b), count(c), count(d), count(distinct a), count(distinct b), count(distinct c), count(distinct d), count(distinct a,b), count(distinct b,c), count(distinct c,d), count(distinct a,d), count(distinct a,c), count(distinct b,d), count(distinct a,b,c), count(distinct b,c,d), count(distinct a,c,d), count(distinct a,b,d), count(distinct a,b,c,d) from abcd
+PREHOOK: type: QUERY
+POSTHOOK: query: --aggregation with literal
+explain select count(1), count(*), count(a), count(b), count(c), count(d), count(distinct a), count(distinct b), count(distinct c), count(distinct d), count(distinct a,b), count(distinct b,c), count(distinct c,d), count(distinct a,d), count(distinct a,c), count(distinct b,d), count(distinct a,b,c), count(distinct b,c,d), count(distinct a,c,d), count(distinct a,b,d), count(distinct a,b,c,d) from abcd
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Tez
+#### A masked pattern was here ####
+ Edges:
+ Reducer 2 <- Map 1 (SIMPLE_EDGE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: abcd
+ Statistics: Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: a (type: int), b (type: int), c (type: int), d (type: int)
+ outputColumnNames: $f1, $f2, $f3, $f4
+ Statistics: Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: $f1 (type: int), $f2 (type: int), $f3 (type: int), $f4 (type: int)
+ sort order: ++++
+ Statistics: Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE
+ Execution mode: llap
+ LLAP IO: no inputs
+ Reducer 2
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: count(1), count(), count(KEY._col0:0._col0), count(KEY._col0:1._col0), count(KEY._col0:2._col0), count(KEY._col0:3._col0), count(DISTINCT KEY._col0:0._col0), count(DISTINCT KEY._col0:1._col0), count(DISTINCT KEY._col0:2._col0), count(DISTINCT KEY._col0:3._col0), count(DISTINCT KEY._col0:4._col0, KEY._col0:4._col1), count(DISTINCT KEY._col0:5._col0, KEY._col0:5._col1), count(DISTINCT KEY._col0:6._col0, KEY._col0:6._col1), count(DISTINCT KEY._col0:7._col0, KEY._col0:7._col1), count(DISTINCT KEY._col0:8._col0, KEY._col0:8._col1), count(DISTINCT KEY._col0:9._col0, KEY._col0:9._col1), count(DISTINCT KEY._col0:10._col0, KEY._col0:10._col1, KEY._col0:10._col2), count(DISTINCT KEY._col0:11._col0, KEY._col0:11._col1, KEY._col0:11._col2), count(DISTINCT KEY._col0:12._col0, KEY._col0:12._col1, KEY._col0:12._col2), count(DISTINCT KEY._col0:13._col0, KEY._col0:13._col1, KEY._col0:13._col2), count(DISTINCT KEY._col0:14._col0, KEY._col0:14._col1, KEY._col0:14._col2, K
EY._col0:14._col3)
+ mode: complete
+ outputColumnNames: $f0, $f1, $f2, $f3, $f4, $f5, $f6, $f7, $f8, $f9, $f10, $f11, $f12, $f13, $f14, $f15, $f16, $f17, $f18, $f19, $f20
+ Statistics: Num rows: 1 Data size: 168 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 168 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
Stage: Stage-0
http://git-wip-us.apache.org/repos/asf/hive/blob/5f01dc42/ql/src/test/results/clientpositive/llap/cross_join.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/cross_join.q.out b/ql/src/test/results/clientpositive/llap/cross_join.q.out
index 6ff8c2d..8578dbf 100644
--- a/ql/src/test/results/clientpositive/llap/cross_join.q.out
+++ b/ql/src/test/results/clientpositive/llap/cross_join.q.out
@@ -1,4 +1,4 @@
-Warning: Shuffle Join MERGEJOIN[11][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product
+Warning: Shuffle Join MERGEJOIN[9][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product
PREHOOK: query: -- current
explain select src.key from src join src src2
PREHOOK: type: QUERY
@@ -12,6 +12,7 @@ STAGE DEPENDENCIES:
STAGE PLANS:
Stage: Stage-1
Tez
+#### A masked pattern was here ####
Edges:
Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE)
#### A masked pattern was here ####
@@ -20,20 +21,21 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: src
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: string)
Execution mode: llap
+ LLAP IO: no inputs
Map 3
Map Operator Tree:
TableScan
- alias: src
+ alias: src2
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE
@@ -41,6 +43,7 @@ STAGE PLANS:
sort order:
Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
+ LLAP IO: no inputs
Reducer 2
Execution mode: llap
Reduce Operator Tree:
@@ -51,13 +54,13 @@ STAGE PLANS:
0
1
outputColumnNames: _col0
- Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 250000 Data size: 21750000 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 250000 Data size: 21750000 Basic stats: COMPLETE Column stats: COMPLETE
table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
Stage: Stage-0
@@ -66,7 +69,7 @@ STAGE PLANS:
Processor Tree:
ListSink
-Warning: Shuffle Join MERGEJOIN[11][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product
+Warning: Shuffle Join MERGEJOIN[9][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product
PREHOOK: query: -- ansi cross join
explain select src.key from src cross join src src2
PREHOOK: type: QUERY
@@ -80,6 +83,7 @@ STAGE DEPENDENCIES:
STAGE PLANS:
Stage: Stage-1
Tez
+#### A masked pattern was here ####
Edges:
Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE)
#### A masked pattern was here ####
@@ -88,20 +92,21 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: src
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: string)
Execution mode: llap
+ LLAP IO: no inputs
Map 3
Map Operator Tree:
TableScan
- alias: src
+ alias: src2
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE
@@ -109,6 +114,7 @@ STAGE PLANS:
sort order:
Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
+ LLAP IO: no inputs
Reducer 2
Execution mode: llap
Reduce Operator Tree:
@@ -119,13 +125,13 @@ STAGE PLANS:
0
1
outputColumnNames: _col0
- Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 250000 Data size: 21750000 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 250000 Data size: 21750000 Basic stats: COMPLETE Column stats: COMPLETE
table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
Stage: Stage-0
@@ -147,6 +153,7 @@ STAGE DEPENDENCIES:
STAGE PLANS:
Stage: Stage-1
Tez
+#### A masked pattern was here ####
Edges:
Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE)
#### A masked pattern was here ####
@@ -155,38 +162,40 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: src
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: key is not null (type: boolean)
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 43500 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: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
+ LLAP IO: no inputs
Map 3
Map Operator Tree:
TableScan
- alias: src
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ alias: src2
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: key is not null (type: boolean)
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 43500 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: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
+ LLAP IO: no inputs
Reducer 2
Execution mode: llap
Reduce Operator Tree:
@@ -197,13 +206,13 @@ STAGE PLANS:
0 _col0 (type: string)
1 _col0 (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1219 Data size: 106053 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1219 Data size: 106053 Basic stats: COMPLETE Column stats: COMPLETE
table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
Stage: Stage-0
@@ -212,3 +221,204 @@ STAGE PLANS:
Processor Tree:
ListSink
+Warning: Map Join MAPJOIN[9][bigTable=?] in task 'Map 1' is a cross product
+PREHOOK: query: explain select src.key from src join src src2
+PREHOOK: type: QUERY
+POSTHOOK: query: explain select src.key from src join src src2
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Tez
+#### A masked pattern was here ####
+ Edges:
+ Map 1 <- Map 2 (BROADCAST_EDGE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: src
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: key (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0
+ 1
+ outputColumnNames: _col0
+ input vertices:
+ 1 Map 2
+ Statistics: Num rows: 250000 Data size: 21750000 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 250000 Data size: 21750000 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
+ Execution mode: llap
+ LLAP IO: no inputs
+ Map 2
+ Map Operator Tree:
+ TableScan
+ alias: src2
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE
+ Execution mode: llap
+ LLAP IO: no inputs
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+Warning: Map Join MAPJOIN[9][bigTable=?] in task 'Map 1' is a cross product
+PREHOOK: query: explain select src.key from src cross join src src2
+PREHOOK: type: QUERY
+POSTHOOK: query: explain select src.key from src cross join src src2
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Tez
+#### A masked pattern was here ####
+ Edges:
+ Map 1 <- Map 2 (BROADCAST_EDGE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: src
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: key (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0
+ 1
+ outputColumnNames: _col0
+ input vertices:
+ 1 Map 2
+ Statistics: Num rows: 250000 Data size: 21750000 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 250000 Data size: 21750000 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
+ Execution mode: llap
+ LLAP IO: no inputs
+ Map 2
+ Map Operator Tree:
+ TableScan
+ alias: src2
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE
+ Execution mode: llap
+ LLAP IO: no inputs
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: explain select src.key from src cross join src src2 on src.key=src2.key
+PREHOOK: type: QUERY
+POSTHOOK: query: explain select src.key from src cross join src src2 on src.key=src2.key
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Tez
+#### A masked pattern was here ####
+ Edges:
+ Map 1 <- Map 2 (BROADCAST_EDGE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: src
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
+ Filter Operator
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: key (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col0 (type: string)
+ 1 _col0 (type: string)
+ outputColumnNames: _col0
+ input vertices:
+ 1 Map 2
+ Statistics: Num rows: 1219 Data size: 106053 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1219 Data size: 106053 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
+ Execution mode: llap
+ LLAP IO: no inputs
+ Map 2
+ Map Operator Tree:
+ TableScan
+ alias: src2
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
+ Filter Operator
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: key (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 500 Data size: 43500 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: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
+ Execution mode: llap
+ LLAP IO: no inputs
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+