You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@hive.apache.org by jd...@apache.org on 2017/01/24 20:02:49 UTC
[2/6] hive git commit: HIVE-15269: Dynamic Min-Max/BloomFilter
runtime-filtering for Tez (Deepak Jaiswal via Jason Dere)
http://git-wip-us.apache.org/repos/asf/hive/blob/cc3fd84e/ql/src/test/results/clientpositive/llap/mergejoin.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/mergejoin.q.out b/ql/src/test/results/clientpositive/llap/mergejoin.q.out
index 9d27a10..4ec2a71 100644
--- a/ql/src/test/results/clientpositive/llap/mergejoin.q.out
+++ b/ql/src/test/results/clientpositive/llap/mergejoin.q.out
@@ -13,17 +13,19 @@ STAGE PLANS:
Tez
#### A masked pattern was here ####
Edges:
+ Map 1 <- Reducer 4 (BROADCAST_EDGE)
Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE)
+ Reducer 4 <- Map 3 (CUSTOM_SIMPLE_EDGE)
#### A masked pattern was here ####
Vertices:
Map 1
Map Operator Tree:
TableScan
alias: a
- filterExpr: key is not null (type: boolean)
+ filterExpr: (key is not null and key BETWEEN DynamicValue(RS_7_b_key_min) AND DynamicValue(RS_7_b_key_max) and in_bloom_filter(key, DynamicValue(RS_7_b_key_bloom_filter))) (type: boolean)
Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: key is not null (type: boolean)
+ predicate: (key is not null and key BETWEEN DynamicValue(RS_7_b_key_min) AND DynamicValue(RS_7_b_key_max) and in_bloom_filter(key, DynamicValue(RS_7_b_key_bloom_filter))) (type: boolean)
Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: string), value (type: string)
@@ -56,6 +58,19 @@ STAGE PLANS:
Map-reduce partition columns: _col0 (type: string)
Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: string)
+ Select Operator
+ expressions: _col0 (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: min(_col0), max(_col0), bloom_filter(_col0, expectedEntries=25)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: binary)
Execution mode: llap
LLAP IO: no inputs
Reducer 2
@@ -76,6 +91,18 @@ 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 4
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: min(VALUE._col0), max(VALUE._col1), bloom_filter(VALUE._col2, expectedEntries=25)
+ mode: final
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: binary)
Stage: Stage-0
Fetch Operator
@@ -257,8 +284,10 @@ STAGE PLANS:
Tez
#### A masked pattern was here ####
Edges:
- Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE)
+ Map 5 <- Reducer 4 (BROADCAST_EDGE)
+ Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE)
Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE)
+ Reducer 4 <- Map 1 (CUSTOM_SIMPLE_EDGE)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -279,16 +308,29 @@ STAGE PLANS:
sort order: +
Map-reduce partition columns: _col0 (type: int)
Statistics: Num rows: 242 Data size: 24684 Basic stats: COMPLETE Column stats: NONE
- Execution mode: vectorized, llap
+ Select Operator
+ expressions: _col0 (type: int)
+ outputColumnNames: _col0
+ Statistics: Num rows: 242 Data size: 24684 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: min(_col0), max(_col0), bloom_filter(_col0, expectedEntries=242)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: int), _col1 (type: int), _col2 (type: binary)
+ Execution mode: llap
LLAP IO: all inputs
- Map 4
+ Map 5
Map Operator Tree:
TableScan
alias: b
- filterExpr: key is not null (type: boolean)
+ filterExpr: (key is not null and key BETWEEN DynamicValue(RS_6_a_key_min) AND DynamicValue(RS_6_a_key_max) and in_bloom_filter(key, DynamicValue(RS_6_a_key_bloom_filter))) (type: boolean)
Statistics: Num rows: 500 Data size: 51000 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: key is not null (type: boolean)
+ predicate: (key is not null and key BETWEEN DynamicValue(RS_6_a_key_min) AND DynamicValue(RS_6_a_key_max) and in_bloom_filter(key, DynamicValue(RS_6_a_key_bloom_filter))) (type: boolean)
Statistics: Num rows: 500 Data size: 51000 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: int)
@@ -299,7 +341,7 @@ STAGE PLANS:
sort order: +
Map-reduce partition columns: _col0 (type: int)
Statistics: Num rows: 500 Data size: 51000 Basic stats: COMPLETE Column stats: NONE
- Execution mode: vectorized, llap
+ Execution mode: llap
LLAP IO: all inputs
Reducer 2
Execution mode: llap
@@ -335,6 +377,18 @@ 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 4
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: min(VALUE._col0), max(VALUE._col1), bloom_filter(VALUE._col2, expectedEntries=242)
+ mode: final
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: int), _col1 (type: int), _col2 (type: binary)
Stage: Stage-0
Fetch Operator
@@ -1347,8 +1401,10 @@ STAGE PLANS:
Tez
#### A masked pattern was here ####
Edges:
- Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE)
+ Map 5 <- Reducer 4 (BROADCAST_EDGE)
+ Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE)
Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE)
+ Reducer 4 <- Map 1 (CUSTOM_SIMPLE_EDGE)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -1365,23 +1421,39 @@ STAGE PLANS:
sort order: +
Map-reduce partition columns: _col0 (type: int)
Statistics: Num rows: 242 Data size: 24684 Basic stats: COMPLETE Column stats: NONE
- Execution mode: vectorized, llap
+ Select Operator
+ expressions: _col0 (type: int)
+ outputColumnNames: _col0
+ Statistics: Num rows: 242 Data size: 24684 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: min(_col0), max(_col0), bloom_filter(_col0, expectedEntries=242)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: int), _col1 (type: int), _col2 (type: binary)
+ Execution mode: llap
LLAP IO: all inputs
- Map 4
+ Map 5
Map Operator Tree:
TableScan
alias: b
Statistics: Num rows: 500 Data size: 51000 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: key (type: int)
- outputColumnNames: _col0
+ Filter Operator
+ predicate: key BETWEEN DynamicValue(RS_4_a_key_min) AND DynamicValue(RS_4_a_key_max) (type: boolean)
Statistics: Num rows: 500 Data size: 51000 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: int)
- sort order: +
- Map-reduce partition columns: _col0 (type: int)
+ Select Operator
+ expressions: key (type: int)
+ outputColumnNames: _col0
Statistics: Num rows: 500 Data size: 51000 Basic stats: COMPLETE Column stats: NONE
- Execution mode: vectorized, llap
+ Reduce Output Operator
+ key expressions: _col0 (type: int)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: int)
+ Statistics: Num rows: 500 Data size: 51000 Basic stats: COMPLETE Column stats: NONE
+ Execution mode: llap
LLAP IO: all inputs
Reducer 2
Execution mode: llap
@@ -1417,6 +1489,18 @@ 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 4
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: min(VALUE._col0), max(VALUE._col1), bloom_filter(VALUE._col2, expectedEntries=242)
+ mode: final
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: int), _col1 (type: int), _col2 (type: binary)
Stage: Stage-0
Fetch Operator
@@ -1458,8 +1542,10 @@ STAGE PLANS:
Tez
#### A masked pattern was here ####
Edges:
+ Map 1 <- Reducer 5 (BROADCAST_EDGE)
Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE)
Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE)
+ Reducer 5 <- Map 4 (CUSTOM_SIMPLE_EDGE)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -1467,16 +1553,19 @@ STAGE PLANS:
TableScan
alias: a
Statistics: Num rows: 242 Data size: 24684 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: key (type: int)
- outputColumnNames: _col0
+ Filter Operator
+ predicate: key BETWEEN DynamicValue(RS_5_b_key_min) AND DynamicValue(RS_5_b_key_max) (type: boolean)
Statistics: Num rows: 242 Data size: 24684 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: int)
- sort order: +
- Map-reduce partition columns: _col0 (type: int)
+ Select Operator
+ expressions: key (type: int)
+ outputColumnNames: _col0
Statistics: Num rows: 242 Data size: 24684 Basic stats: COMPLETE Column stats: NONE
- Execution mode: vectorized, llap
+ Reduce Output Operator
+ key expressions: _col0 (type: int)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: int)
+ Statistics: Num rows: 242 Data size: 24684 Basic stats: COMPLETE Column stats: NONE
+ Execution mode: llap
LLAP IO: all inputs
Map 4
Map Operator Tree:
@@ -1492,7 +1581,20 @@ STAGE PLANS:
sort order: +
Map-reduce partition columns: _col0 (type: int)
Statistics: Num rows: 500 Data size: 51000 Basic stats: COMPLETE Column stats: NONE
- Execution mode: vectorized, llap
+ Select Operator
+ expressions: _col0 (type: int)
+ outputColumnNames: _col0
+ Statistics: Num rows: 500 Data size: 51000 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: min(_col0), max(_col0), bloom_filter(_col0, expectedEntries=500)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: int), _col1 (type: int), _col2 (type: binary)
+ Execution mode: llap
LLAP IO: all inputs
Reducer 2
Execution mode: llap
@@ -1528,6 +1630,18 @@ 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 5
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: min(VALUE._col0), max(VALUE._col1), bloom_filter(VALUE._col2, expectedEntries=500)
+ mode: final
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: int), _col1 (type: int), _col2 (type: binary)
Stage: Stage-0
Fetch Operator
@@ -1676,19 +1790,23 @@ STAGE PLANS:
Tez
#### A masked pattern was here ####
Edges:
- Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE)
- Reducer 3 <- Map 6 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE)
+ Map 1 <- Reducer 8 (BROADCAST_EDGE)
+ Map 6 <- Reducer 5 (BROADCAST_EDGE)
+ Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 6 (SIMPLE_EDGE)
+ Reducer 3 <- Map 7 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE)
Reducer 4 <- Reducer 3 (CUSTOM_SIMPLE_EDGE)
+ Reducer 5 <- Map 1 (CUSTOM_SIMPLE_EDGE)
+ Reducer 8 <- Map 7 (CUSTOM_SIMPLE_EDGE)
#### A masked pattern was here ####
Vertices:
Map 1
Map Operator Tree:
TableScan
alias: a
- filterExpr: (key is not null and value is not null) (type: boolean)
+ filterExpr: (key is not null and value is not null and value BETWEEN DynamicValue(RS_13_c_value_min) AND DynamicValue(RS_13_c_value_max) and in_bloom_filter(value, DynamicValue(RS_13_c_value_bloom_filter))) (type: boolean)
Statistics: Num rows: 242 Data size: 24684 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: (key is not null and value is not null) (type: boolean)
+ predicate: (key is not null and value is not null and value BETWEEN DynamicValue(RS_13_c_value_min) AND DynamicValue(RS_13_c_value_max) and in_bloom_filter(value, DynamicValue(RS_13_c_value_bloom_filter))) (type: boolean)
Statistics: Num rows: 242 Data size: 24684 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: int), value (type: string)
@@ -1700,16 +1818,29 @@ STAGE PLANS:
Map-reduce partition columns: _col0 (type: int)
Statistics: Num rows: 242 Data size: 24684 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: string)
- Execution mode: vectorized, llap
+ Select Operator
+ expressions: _col0 (type: int)
+ outputColumnNames: _col0
+ Statistics: Num rows: 242 Data size: 24684 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: min(_col0), max(_col0), bloom_filter(_col0, expectedEntries=242)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: int), _col1 (type: int), _col2 (type: binary)
+ Execution mode: llap
LLAP IO: all inputs
- Map 5
+ Map 6
Map Operator Tree:
TableScan
alias: b
- filterExpr: key is not null (type: boolean)
+ filterExpr: (key is not null and key BETWEEN DynamicValue(RS_9_a_key_min) AND DynamicValue(RS_9_a_key_max) and in_bloom_filter(key, DynamicValue(RS_9_a_key_bloom_filter))) (type: boolean)
Statistics: Num rows: 500 Data size: 51000 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: key is not null (type: boolean)
+ predicate: (key is not null and key BETWEEN DynamicValue(RS_9_a_key_min) AND DynamicValue(RS_9_a_key_max) and in_bloom_filter(key, DynamicValue(RS_9_a_key_bloom_filter))) (type: boolean)
Statistics: Num rows: 500 Data size: 51000 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: int)
@@ -1720,9 +1851,9 @@ STAGE PLANS:
sort order: +
Map-reduce partition columns: _col0 (type: int)
Statistics: Num rows: 500 Data size: 51000 Basic stats: COMPLETE Column stats: NONE
- Execution mode: vectorized, llap
+ Execution mode: llap
LLAP IO: all inputs
- Map 6
+ Map 7
Map Operator Tree:
TableScan
alias: c
@@ -1740,6 +1871,19 @@ STAGE PLANS:
sort order: +
Map-reduce partition columns: _col0 (type: string)
Statistics: Num rows: 25 Data size: 2225 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: _col0 (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 25 Data size: 2225 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: min(_col0), max(_col0), bloom_filter(_col0, expectedEntries=25)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: binary)
Execution mode: llap
LLAP IO: no inputs
Reducer 2
@@ -1792,6 +1936,30 @@ 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 5
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: min(VALUE._col0), max(VALUE._col1), bloom_filter(VALUE._col2, expectedEntries=242)
+ mode: final
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: int), _col1 (type: int), _col2 (type: binary)
+ Reducer 8
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: min(VALUE._col0), max(VALUE._col1), bloom_filter(VALUE._col2, expectedEntries=25)
+ mode: final
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: binary)
Stage: Stage-0
Fetch Operator
@@ -1829,8 +1997,10 @@ STAGE PLANS:
Tez
#### A masked pattern was here ####
Edges:
- Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE)
+ Map 5 <- Reducer 4 (BROADCAST_EDGE)
+ Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE)
Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE)
+ Reducer 4 <- Map 1 (CUSTOM_SIMPLE_EDGE)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -1851,16 +2021,29 @@ STAGE PLANS:
sort order: +
Map-reduce partition columns: _col1 (type: string)
Statistics: Num rows: 242 Data size: 24684 Basic stats: COMPLETE Column stats: NONE
- Execution mode: vectorized, llap
+ Select Operator
+ expressions: _col1 (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 242 Data size: 24684 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: min(_col0), max(_col0), bloom_filter(_col0, expectedEntries=242)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: binary)
+ Execution mode: llap
LLAP IO: all inputs
- Map 4
+ Map 5
Map Operator Tree:
TableScan
alias: b
- filterExpr: value is not null (type: boolean)
+ filterExpr: (value is not null and value BETWEEN DynamicValue(RS_6_a_value_min) AND DynamicValue(RS_6_a_value_max) and in_bloom_filter(value, DynamicValue(RS_6_a_value_bloom_filter))) (type: boolean)
Statistics: Num rows: 500 Data size: 51000 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: value is not null (type: boolean)
+ predicate: (value is not null and value BETWEEN DynamicValue(RS_6_a_value_min) AND DynamicValue(RS_6_a_value_max) and in_bloom_filter(value, DynamicValue(RS_6_a_value_bloom_filter))) (type: boolean)
Statistics: Num rows: 500 Data size: 51000 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: value (type: string)
@@ -1871,7 +2054,7 @@ STAGE PLANS:
sort order: +
Map-reduce partition columns: _col1 (type: string)
Statistics: Num rows: 500 Data size: 51000 Basic stats: COMPLETE Column stats: NONE
- Execution mode: vectorized, llap
+ Execution mode: llap
LLAP IO: all inputs
Reducer 2
Execution mode: llap
@@ -1907,6 +2090,18 @@ 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 4
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: min(VALUE._col0), max(VALUE._col1), bloom_filter(VALUE._col2, expectedEntries=242)
+ mode: final
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: binary)
Stage: Stage-0
Fetch Operator
@@ -1950,10 +2145,12 @@ STAGE PLANS:
Tez
#### A masked pattern was here ####
Edges:
- Map 7 <- Union 3 (CONTAINS)
- Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 6 (SIMPLE_EDGE), Union 3 (CONTAINS)
- Reducer 4 <- Map 8 (SIMPLE_EDGE), Union 3 (SIMPLE_EDGE)
+ Map 8 <- Union 3 (CONTAINS)
+ Map 9 <- Reducer 6 (BROADCAST_EDGE)
+ Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 7 (SIMPLE_EDGE), Union 3 (CONTAINS)
+ Reducer 4 <- Map 9 (SIMPLE_EDGE), Union 3 (SIMPLE_EDGE)
Reducer 5 <- Reducer 4 (CUSTOM_SIMPLE_EDGE)
+ Reducer 6 <- Union 3 (CUSTOM_SIMPLE_EDGE)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -1976,7 +2173,7 @@ STAGE PLANS:
Statistics: Num rows: 242 Data size: 24684 Basic stats: COMPLETE Column stats: NONE
Execution mode: vectorized, llap
LLAP IO: all inputs
- Map 6
+ Map 7
Map Operator Tree:
TableScan
alias: s3
@@ -1996,7 +2193,7 @@ STAGE PLANS:
Statistics: Num rows: 242 Data size: 24684 Basic stats: COMPLETE Column stats: NONE
Execution mode: vectorized, llap
LLAP IO: all inputs
- Map 7
+ Map 8
Map Operator Tree:
TableScan
alias: s2
@@ -2014,16 +2211,29 @@ STAGE PLANS:
sort order: +
Map-reduce partition columns: _col0 (type: int)
Statistics: Num rows: 508 Data size: 51836 Basic stats: COMPLETE Column stats: NONE
- Execution mode: vectorized, llap
+ Select Operator
+ expressions: _col0 (type: int)
+ outputColumnNames: _col0
+ Statistics: Num rows: 508 Data size: 51836 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: min(_col0), max(_col0), bloom_filter(_col0, expectedEntries=508)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: int), _col1 (type: int), _col2 (type: binary)
+ Execution mode: llap
LLAP IO: all inputs
- Map 8
+ Map 9
Map Operator Tree:
TableScan
alias: b
- filterExpr: key is not null (type: boolean)
+ filterExpr: (key is not null and key BETWEEN DynamicValue(RS_18_s1_key_min) AND DynamicValue(RS_18_s1_key_max) and in_bloom_filter(key, DynamicValue(RS_18_s1_key_bloom_filter))) (type: boolean)
Statistics: Num rows: 500 Data size: 51000 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: key is not null (type: boolean)
+ predicate: (key is not null and key BETWEEN DynamicValue(RS_18_s1_key_min) AND DynamicValue(RS_18_s1_key_max) and in_bloom_filter(key, DynamicValue(RS_18_s1_key_bloom_filter))) (type: boolean)
Statistics: Num rows: 500 Data size: 51000 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: int)
@@ -2034,7 +2244,7 @@ STAGE PLANS:
sort order: +
Map-reduce partition columns: _col0 (type: int)
Statistics: Num rows: 500 Data size: 51000 Basic stats: COMPLETE Column stats: NONE
- Execution mode: vectorized, llap
+ Execution mode: llap
LLAP IO: all inputs
Reducer 2
Execution mode: llap
@@ -2052,6 +2262,19 @@ STAGE PLANS:
sort order: +
Map-reduce partition columns: _col0 (type: int)
Statistics: Num rows: 508 Data size: 51836 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: int)
+ outputColumnNames: _col0
+ Statistics: Num rows: 508 Data size: 51836 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: min(_col0), max(_col0), bloom_filter(_col0, expectedEntries=508)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: int), _col1 (type: int), _col2 (type: binary)
Reducer 4
Execution mode: llap
Reduce Operator Tree:
@@ -2086,6 +2309,18 @@ 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 6
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: min(VALUE._col0), max(VALUE._col1), bloom_filter(VALUE._col2, expectedEntries=508)
+ mode: final
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: int), _col1 (type: int), _col2 (type: binary)
Union 3
Vertex: Union 3
@@ -2108,8 +2343,10 @@ STAGE PLANS:
Tez
#### A masked pattern was here ####
Edges:
- Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE)
+ Map 5 <- Reducer 4 (BROADCAST_EDGE)
+ Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE)
Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE)
+ Reducer 4 <- Map 1 (CUSTOM_SIMPLE_EDGE)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -2130,16 +2367,29 @@ STAGE PLANS:
sort order: +
Map-reduce partition columns: _col1 (type: string)
Statistics: Num rows: 242 Data size: 24684 Basic stats: COMPLETE Column stats: NONE
- Execution mode: vectorized, llap
+ Select Operator
+ expressions: _col1 (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 242 Data size: 24684 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: min(_col0), max(_col0), bloom_filter(_col0, expectedEntries=242)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: binary)
+ Execution mode: llap
LLAP IO: all inputs
- Map 4
+ Map 5
Map Operator Tree:
TableScan
alias: b
- filterExpr: value is not null (type: boolean)
+ filterExpr: (value is not null and value BETWEEN DynamicValue(RS_6_a_value_min) AND DynamicValue(RS_6_a_value_max) and in_bloom_filter(value, DynamicValue(RS_6_a_value_bloom_filter))) (type: boolean)
Statistics: Num rows: 500 Data size: 51000 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: value is not null (type: boolean)
+ predicate: (value is not null and value BETWEEN DynamicValue(RS_6_a_value_min) AND DynamicValue(RS_6_a_value_max) and in_bloom_filter(value, DynamicValue(RS_6_a_value_bloom_filter))) (type: boolean)
Statistics: Num rows: 500 Data size: 51000 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: value (type: string)
@@ -2150,7 +2400,7 @@ STAGE PLANS:
sort order: +
Map-reduce partition columns: _col1 (type: string)
Statistics: Num rows: 500 Data size: 51000 Basic stats: COMPLETE Column stats: NONE
- Execution mode: vectorized, llap
+ Execution mode: llap
LLAP IO: all inputs
Reducer 2
Execution mode: llap
@@ -2186,6 +2436,18 @@ 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 4
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: min(VALUE._col0), max(VALUE._col1), bloom_filter(VALUE._col2, expectedEntries=242)
+ mode: final
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: binary)
Stage: Stage-0
Fetch Operator
@@ -2221,19 +2483,23 @@ STAGE PLANS:
Tez
#### A masked pattern was here ####
Edges:
- Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE)
- Reducer 3 <- Map 6 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE)
+ Map 1 <- Reducer 8 (BROADCAST_EDGE)
+ Map 6 <- Reducer 5 (BROADCAST_EDGE)
+ Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 6 (SIMPLE_EDGE)
+ Reducer 3 <- Map 7 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE)
Reducer 4 <- Reducer 3 (CUSTOM_SIMPLE_EDGE)
+ Reducer 5 <- Map 1 (CUSTOM_SIMPLE_EDGE)
+ Reducer 8 <- Map 7 (CUSTOM_SIMPLE_EDGE)
#### A masked pattern was here ####
Vertices:
Map 1
Map Operator Tree:
TableScan
alias: a
- filterExpr: (key is not null and value is not null) (type: boolean)
+ filterExpr: (key is not null and value is not null and value BETWEEN DynamicValue(RS_13_c_value_min) AND DynamicValue(RS_13_c_value_max) and in_bloom_filter(value, DynamicValue(RS_13_c_value_bloom_filter))) (type: boolean)
Statistics: Num rows: 242 Data size: 24684 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: (key is not null and value is not null) (type: boolean)
+ predicate: (key is not null and value is not null and value BETWEEN DynamicValue(RS_13_c_value_min) AND DynamicValue(RS_13_c_value_max) and in_bloom_filter(value, DynamicValue(RS_13_c_value_bloom_filter))) (type: boolean)
Statistics: Num rows: 242 Data size: 24684 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: int), value (type: string)
@@ -2245,16 +2511,29 @@ STAGE PLANS:
Map-reduce partition columns: _col0 (type: int)
Statistics: Num rows: 242 Data size: 24684 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: string)
- Execution mode: vectorized, llap
+ Select Operator
+ expressions: _col0 (type: int)
+ outputColumnNames: _col0
+ Statistics: Num rows: 242 Data size: 24684 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: min(_col0), max(_col0), bloom_filter(_col0, expectedEntries=242)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: int), _col1 (type: int), _col2 (type: binary)
+ Execution mode: llap
LLAP IO: all inputs
- Map 5
+ Map 6
Map Operator Tree:
TableScan
alias: b
- filterExpr: key is not null (type: boolean)
+ filterExpr: (key is not null and key BETWEEN DynamicValue(RS_9_a_key_min) AND DynamicValue(RS_9_a_key_max) and in_bloom_filter(key, DynamicValue(RS_9_a_key_bloom_filter))) (type: boolean)
Statistics: Num rows: 500 Data size: 51000 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: key is not null (type: boolean)
+ predicate: (key is not null and key BETWEEN DynamicValue(RS_9_a_key_min) AND DynamicValue(RS_9_a_key_max) and in_bloom_filter(key, DynamicValue(RS_9_a_key_bloom_filter))) (type: boolean)
Statistics: Num rows: 500 Data size: 51000 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: int)
@@ -2265,9 +2544,9 @@ STAGE PLANS:
sort order: +
Map-reduce partition columns: _col0 (type: int)
Statistics: Num rows: 500 Data size: 51000 Basic stats: COMPLETE Column stats: NONE
- Execution mode: vectorized, llap
+ Execution mode: llap
LLAP IO: all inputs
- Map 6
+ Map 7
Map Operator Tree:
TableScan
alias: c
@@ -2285,6 +2564,19 @@ STAGE PLANS:
sort order: +
Map-reduce partition columns: _col0 (type: string)
Statistics: Num rows: 25 Data size: 2225 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: _col0 (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 25 Data size: 2225 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: min(_col0), max(_col0), bloom_filter(_col0, expectedEntries=25)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: binary)
Execution mode: llap
LLAP IO: no inputs
Reducer 2
@@ -2337,6 +2629,30 @@ 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 5
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: min(VALUE._col0), max(VALUE._col1), bloom_filter(VALUE._col2, expectedEntries=242)
+ mode: final
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: int), _col1 (type: int), _col2 (type: binary)
+ Reducer 8
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: min(VALUE._col0), max(VALUE._col1), bloom_filter(VALUE._col2, expectedEntries=25)
+ mode: final
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: binary)
Stage: Stage-0
Fetch Operator
@@ -2382,10 +2698,12 @@ STAGE PLANS:
Tez
#### A masked pattern was here ####
Edges:
- Map 7 <- Union 3 (CONTAINS)
- Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 6 (SIMPLE_EDGE), Union 3 (CONTAINS)
- Reducer 4 <- Map 8 (SIMPLE_EDGE), Union 3 (SIMPLE_EDGE)
+ Map 8 <- Union 3 (CONTAINS)
+ Map 9 <- Reducer 6 (BROADCAST_EDGE)
+ Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 7 (SIMPLE_EDGE), Union 3 (CONTAINS)
+ Reducer 4 <- Map 9 (SIMPLE_EDGE), Union 3 (SIMPLE_EDGE)
Reducer 5 <- Reducer 4 (CUSTOM_SIMPLE_EDGE)
+ Reducer 6 <- Union 3 (CUSTOM_SIMPLE_EDGE)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -2408,7 +2726,7 @@ STAGE PLANS:
Statistics: Num rows: 242 Data size: 24684 Basic stats: COMPLETE Column stats: NONE
Execution mode: vectorized, llap
LLAP IO: all inputs
- Map 6
+ Map 7
Map Operator Tree:
TableScan
alias: s3
@@ -2428,7 +2746,7 @@ STAGE PLANS:
Statistics: Num rows: 242 Data size: 24684 Basic stats: COMPLETE Column stats: NONE
Execution mode: vectorized, llap
LLAP IO: all inputs
- Map 7
+ Map 8
Map Operator Tree:
TableScan
alias: s2
@@ -2446,16 +2764,29 @@ STAGE PLANS:
sort order: +
Map-reduce partition columns: _col0 (type: int)
Statistics: Num rows: 508 Data size: 51836 Basic stats: COMPLETE Column stats: NONE
- Execution mode: vectorized, llap
+ Select Operator
+ expressions: _col0 (type: int)
+ outputColumnNames: _col0
+ Statistics: Num rows: 508 Data size: 51836 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: min(_col0), max(_col0), bloom_filter(_col0, expectedEntries=508)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: int), _col1 (type: int), _col2 (type: binary)
+ Execution mode: llap
LLAP IO: all inputs
- Map 8
+ Map 9
Map Operator Tree:
TableScan
alias: b
- filterExpr: key is not null (type: boolean)
+ filterExpr: (key is not null and key BETWEEN DynamicValue(RS_18_s1_key_min) AND DynamicValue(RS_18_s1_key_max) and in_bloom_filter(key, DynamicValue(RS_18_s1_key_bloom_filter))) (type: boolean)
Statistics: Num rows: 500 Data size: 51000 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: key is not null (type: boolean)
+ predicate: (key is not null and key BETWEEN DynamicValue(RS_18_s1_key_min) AND DynamicValue(RS_18_s1_key_max) and in_bloom_filter(key, DynamicValue(RS_18_s1_key_bloom_filter))) (type: boolean)
Statistics: Num rows: 500 Data size: 51000 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: int)
@@ -2466,7 +2797,7 @@ STAGE PLANS:
sort order: +
Map-reduce partition columns: _col0 (type: int)
Statistics: Num rows: 500 Data size: 51000 Basic stats: COMPLETE Column stats: NONE
- Execution mode: vectorized, llap
+ Execution mode: llap
LLAP IO: all inputs
Reducer 2
Execution mode: llap
@@ -2484,6 +2815,19 @@ STAGE PLANS:
sort order: +
Map-reduce partition columns: _col0 (type: int)
Statistics: Num rows: 508 Data size: 51836 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: int)
+ outputColumnNames: _col0
+ Statistics: Num rows: 508 Data size: 51836 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: min(_col0), max(_col0), bloom_filter(_col0, expectedEntries=508)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: int), _col1 (type: int), _col2 (type: binary)
Reducer 4
Execution mode: llap
Reduce Operator Tree:
@@ -2518,6 +2862,18 @@ 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 6
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: min(VALUE._col0), max(VALUE._col1), bloom_filter(VALUE._col2, expectedEntries=508)
+ mode: final
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: int), _col1 (type: int), _col2 (type: binary)
Union 3
Vertex: Union 3
@@ -2554,10 +2910,12 @@ STAGE PLANS:
Tez
#### A masked pattern was here ####
Edges:
+ Map 6 <- Reducer 5 (BROADCAST_EDGE)
Reducer 2 <- Map 1 (SIMPLE_EDGE)
- Reducer 3 <- Reducer 2 (SIMPLE_EDGE), Reducer 6 (SIMPLE_EDGE)
+ Reducer 3 <- Reducer 2 (SIMPLE_EDGE), Reducer 7 (SIMPLE_EDGE)
Reducer 4 <- Reducer 3 (CUSTOM_SIMPLE_EDGE)
- Reducer 6 <- Map 5 (SIMPLE_EDGE)
+ Reducer 5 <- Reducer 2 (CUSTOM_SIMPLE_EDGE)
+ Reducer 7 <- Map 6 (SIMPLE_EDGE)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -2579,14 +2937,14 @@ STAGE PLANS:
Statistics: Num rows: 242 Data size: 24684 Basic stats: COMPLETE Column stats: NONE
Execution mode: vectorized, llap
LLAP IO: all inputs
- Map 5
+ Map 6
Map Operator Tree:
TableScan
alias: t2
- filterExpr: key is not null (type: boolean)
+ filterExpr: (key is not null and key BETWEEN DynamicValue(RS_12_t1_key_min) AND DynamicValue(RS_12_t1_key_max) and in_bloom_filter(key, DynamicValue(RS_12_t1_key_bloom_filter))) (type: boolean)
Statistics: Num rows: 500 Data size: 51000 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: key is not null (type: boolean)
+ predicate: (key is not null and key BETWEEN DynamicValue(RS_12_t1_key_min) AND DynamicValue(RS_12_t1_key_max) and in_bloom_filter(key, DynamicValue(RS_12_t1_key_bloom_filter))) (type: boolean)
Statistics: Num rows: 500 Data size: 51000 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: int), value (type: string)
@@ -2596,10 +2954,10 @@ STAGE PLANS:
key expressions: _col0 (type: int), _col1 (type: string)
sort order: ++
Statistics: Num rows: 500 Data size: 51000 Basic stats: COMPLETE Column stats: NONE
- Execution mode: vectorized, llap
+ Execution mode: llap
LLAP IO: all inputs
Reducer 2
- Execution mode: vectorized, llap
+ Execution mode: llap
Reduce Operator Tree:
Select Operator
expressions: KEY.reducesinkkey0 (type: int)
@@ -2610,6 +2968,19 @@ STAGE PLANS:
sort order: +
Map-reduce partition columns: _col0 (type: int)
Statistics: Num rows: 242 Data size: 24684 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: int)
+ outputColumnNames: _col0
+ Statistics: Num rows: 242 Data size: 24684 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: min(_col0), max(_col0), bloom_filter(_col0, expectedEntries=242)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: int), _col1 (type: int), _col2 (type: binary)
Reducer 3
Execution mode: llap
Reduce Operator Tree:
@@ -2644,7 +3015,19 @@ 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 6
+ Reducer 5
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: min(VALUE._col0), max(VALUE._col1), bloom_filter(VALUE._col2, expectedEntries=242)
+ mode: final
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: int), _col1 (type: int), _col2 (type: binary)
+ Reducer 7
Execution mode: vectorized, llap
Reduce Operator Tree:
Select Operator
@@ -3820,7 +4203,7 @@ NULL NULL NULL NULL NULL NULL 97 val_97 2008-04-08
NULL NULL NULL NULL NULL NULL 97 val_97 2008-04-08
NULL NULL NULL NULL NULL NULL 98 val_98 2008-04-08
NULL NULL NULL NULL NULL NULL 98 val_98 2008-04-08
-Warning: Shuffle Join MERGEJOIN[25][tables = [a, b]] in Stage 'Reducer 2' is a cross product
+Warning: Shuffle Join MERGEJOIN[30][tables = [a, b]] in Stage 'Reducer 2' is a cross product
PREHOOK: query: select * from
(select * from tab where tab.key = 0)a
full outer join
http://git-wip-us.apache.org/repos/asf/hive/blob/cc3fd84e/ql/src/test/results/clientpositive/llap/orc_llap.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/orc_llap.q.out b/ql/src/test/results/clientpositive/llap/orc_llap.q.out
index 6b6706e..90055a5 100644
--- a/ql/src/test/results/clientpositive/llap/orc_llap.q.out
+++ b/ql/src/test/results/clientpositive/llap/orc_llap.q.out
@@ -559,8 +559,10 @@ STAGE PLANS:
Tez
#### A masked pattern was here ####
Edges:
- Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE)
+ Map 5 <- Reducer 4 (BROADCAST_EDGE)
+ Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE)
Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE)
+ Reducer 4 <- Map 1 (CUSTOM_SIMPLE_EDGE)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -582,16 +584,29 @@ STAGE PLANS:
Map-reduce partition columns: _col0 (type: smallint)
Statistics: Num rows: 122880 Data size: 29079940 Basic stats: COMPLETE Column stats: NONE
value expressions: _col2 (type: string)
- Execution mode: vectorized, llap
+ Select Operator
+ expressions: _col0 (type: smallint)
+ outputColumnNames: _col0
+ Statistics: Num rows: 122880 Data size: 29079940 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: min(_col0), max(_col0), bloom_filter(_col0, expectedEntries=122880)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: smallint), _col1 (type: smallint), _col2 (type: binary)
+ Execution mode: llap
LLAP IO: all inputs
- Map 4
+ Map 5
Map Operator Tree:
TableScan
alias: o2
- filterExpr: (csmallint is not null and cbigint is not null) (type: boolean)
+ filterExpr: (csmallint is not null and cbigint is not null and csmallint BETWEEN DynamicValue(RS_6_o1_csmallint_min) AND DynamicValue(RS_6_o1_csmallint_max) and in_bloom_filter(csmallint, DynamicValue(RS_6_o1_csmallint_bloom_filter))) (type: boolean)
Statistics: Num rows: 122880 Data size: 29079940 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: (csmallint is not null and cbigint is not null) (type: boolean)
+ predicate: (csmallint is not null and cbigint is not null and csmallint BETWEEN DynamicValue(RS_6_o1_csmallint_min) AND DynamicValue(RS_6_o1_csmallint_max) and in_bloom_filter(csmallint, DynamicValue(RS_6_o1_csmallint_bloom_filter))) (type: boolean)
Statistics: Num rows: 122880 Data size: 29079940 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: csmallint (type: smallint), cstring2 (type: string)
@@ -603,7 +618,7 @@ STAGE PLANS:
Map-reduce partition columns: _col0 (type: smallint)
Statistics: Num rows: 122880 Data size: 29079940 Basic stats: COMPLETE Column stats: NONE
value expressions: _col2 (type: string)
- Execution mode: vectorized, llap
+ Execution mode: llap
LLAP IO: all inputs
Reducer 2
Execution mode: llap
@@ -644,6 +659,18 @@ 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 4
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: min(VALUE._col0), max(VALUE._col1), bloom_filter(VALUE._col2, expectedEntries=122880)
+ mode: final
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: smallint), _col1 (type: smallint), _col2 (type: binary)
Stage: Stage-0
Fetch Operator
@@ -1024,8 +1051,10 @@ STAGE PLANS:
Tez
#### A masked pattern was here ####
Edges:
- Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE)
+ Map 5 <- Reducer 4 (BROADCAST_EDGE)
+ Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE)
Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE)
+ Reducer 4 <- Map 1 (CUSTOM_SIMPLE_EDGE)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -1047,16 +1076,29 @@ STAGE PLANS:
Map-reduce partition columns: _col0 (type: smallint)
Statistics: Num rows: 245760 Data size: 58159880 Basic stats: COMPLETE Column stats: NONE
value expressions: _col2 (type: string)
- Execution mode: vectorized, llap
+ Select Operator
+ expressions: _col0 (type: smallint)
+ outputColumnNames: _col0
+ Statistics: Num rows: 245760 Data size: 58159880 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: min(_col0), max(_col0), bloom_filter(_col0, expectedEntries=245760)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: smallint), _col1 (type: smallint), _col2 (type: binary)
+ Execution mode: llap
LLAP IO: all inputs
- Map 4
+ Map 5
Map Operator Tree:
TableScan
alias: o2
- filterExpr: (csmallint is not null and cbigint is not null) (type: boolean)
+ filterExpr: (csmallint is not null and cbigint is not null and csmallint BETWEEN DynamicValue(RS_6_o1_csmallint_min) AND DynamicValue(RS_6_o1_csmallint_max) and in_bloom_filter(csmallint, DynamicValue(RS_6_o1_csmallint_bloom_filter))) (type: boolean)
Statistics: Num rows: 245760 Data size: 58159880 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: (csmallint is not null and cbigint is not null) (type: boolean)
+ predicate: (csmallint is not null and cbigint is not null and csmallint BETWEEN DynamicValue(RS_6_o1_csmallint_min) AND DynamicValue(RS_6_o1_csmallint_max) and in_bloom_filter(csmallint, DynamicValue(RS_6_o1_csmallint_bloom_filter))) (type: boolean)
Statistics: Num rows: 245760 Data size: 58159880 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: csmallint (type: smallint), cstring2 (type: string)
@@ -1068,7 +1110,7 @@ STAGE PLANS:
Map-reduce partition columns: _col0 (type: smallint)
Statistics: Num rows: 245760 Data size: 58159880 Basic stats: COMPLETE Column stats: NONE
value expressions: _col2 (type: string)
- Execution mode: vectorized, llap
+ Execution mode: llap
LLAP IO: all inputs
Reducer 2
Execution mode: llap
@@ -1109,6 +1151,18 @@ 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 4
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: min(VALUE._col0), max(VALUE._col1), bloom_filter(VALUE._col2, expectedEntries=245760)
+ mode: final
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: smallint), _col1 (type: smallint), _col2 (type: binary)
Stage: Stage-0
Fetch Operator
http://git-wip-us.apache.org/repos/asf/hive/blob/cc3fd84e/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 09b0a83..3be4b6a 100644
--- a/ql/src/test/results/clientpositive/llap/subquery_scalar.q.out
+++ b/ql/src/test/results/clientpositive/llap/subquery_scalar.q.out
@@ -2652,9 +2652,9 @@ POSTHOOK: Input: default@part_null
42669 almond antique medium spring khaki Manufacturer#5 Brand#51 STANDARD BURNISHED TIN 6 MED CAN 1611.66 sits haggl
195606 almond aquamarine sandy cyan gainsboro Manufacturer#2 Brand#25 STANDARD PLATED TIN 18 SM PKG 1701.6 ic de
144293 almond antique olive coral navajo Manufacturer#3 Brand#34 STANDARD POLISHED STEEL 45 JUMBO CAN 1337.29 ag furiously about
-Warning: Shuffle Join MERGEJOIN[94][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 2' is a cross product
-Warning: Shuffle Join MERGEJOIN[91][tables = [$hdt$_4, $hdt$_5]] in Stage 'Reducer 12' is a cross product
-Warning: Shuffle Join MERGEJOIN[92][tables = [$hdt$_4, $hdt$_5, $hdt$_6]] in Stage 'Reducer 13' is a cross product
+Warning: Shuffle Join MERGEJOIN[91][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 2' is a cross product
+Warning: Shuffle Join MERGEJOIN[92][tables = [$hdt$_4, $hdt$_5]] in Stage 'Reducer 12' is a cross product
+Warning: Shuffle Join MERGEJOIN[93][tables = [$hdt$_4, $hdt$_5, $hdt$_6]] in Stage 'Reducer 13' is a cross product
PREHOOK: query: explain select * from part where p_brand <> (select min(p_brand) from part ) AND p_size IN (select (p_size) from part p where p.p_type = part.p_type ) AND p_size <> 340
PREHOOK: type: QUERY
POSTHOOK: query: explain select * from part where p_brand <> (select min(p_brand) from part ) AND p_size IN (select (p_size) from part p where p.p_type = part.p_type ) AND p_size <> 340
@@ -3020,9 +3020,9 @@ STAGE PLANS:
Processor Tree:
ListSink
-Warning: Shuffle Join MERGEJOIN[94][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 2' is a cross product
-Warning: Shuffle Join MERGEJOIN[91][tables = [$hdt$_4, $hdt$_5]] in Stage 'Reducer 12' is a cross product
-Warning: Shuffle Join MERGEJOIN[92][tables = [$hdt$_4, $hdt$_5, $hdt$_6]] in Stage 'Reducer 13' is a cross product
+Warning: Shuffle Join MERGEJOIN[91][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 2' is a cross product
+Warning: Shuffle Join MERGEJOIN[92][tables = [$hdt$_4, $hdt$_5]] in Stage 'Reducer 12' is a cross product
+Warning: Shuffle Join MERGEJOIN[93][tables = [$hdt$_4, $hdt$_5, $hdt$_6]] in Stage 'Reducer 13' is a cross product
PREHOOK: query: select * from part where p_brand <> (select min(p_brand) from part ) AND p_size IN (select (p_size) from part p where p.p_type = part.p_type ) AND p_size <> 340
PREHOOK: type: QUERY
PREHOOK: Input: default@part
@@ -5581,7 +5581,7 @@ POSTHOOK: Input: default@lineitem
175839 874
182052 9607
Warning: Shuffle Join MERGEJOIN[98][tables = [$hdt$_3, $hdt$_4]] in Stage 'Reducer 9' is a cross product
-Warning: Shuffle Join MERGEJOIN[100][tables = [$hdt$_4, $hdt$_5]] in Stage 'Reducer 16' is a cross product
+Warning: Shuffle Join MERGEJOIN[99][tables = [$hdt$_4, $hdt$_5]] in Stage 'Reducer 16' is a cross product
PREHOOK: query: explain select sum(l_extendedprice) from lineitem, part where p_partkey = l_partkey and l_quantity > (select avg(l_quantity) from lineitem where l_partkey = p_partkey)
PREHOOK: type: QUERY
POSTHOOK: query: explain select sum(l_extendedprice) from lineitem, part where p_partkey = l_partkey and l_quantity > (select avg(l_quantity) from lineitem where l_partkey = p_partkey)
@@ -5946,7 +5946,7 @@ STAGE PLANS:
ListSink
Warning: Shuffle Join MERGEJOIN[98][tables = [$hdt$_3, $hdt$_4]] in Stage 'Reducer 9' is a cross product
-Warning: Shuffle Join MERGEJOIN[100][tables = [$hdt$_4, $hdt$_5]] in Stage 'Reducer 16' is a cross product
+Warning: Shuffle Join MERGEJOIN[99][tables = [$hdt$_4, $hdt$_5]] in Stage 'Reducer 16' is a cross product
PREHOOK: query: select sum(l_extendedprice) from lineitem, part where p_partkey = l_partkey and l_quantity > (select avg(l_quantity) from lineitem where l_partkey = p_partkey)
PREHOOK: type: QUERY
PREHOOK: Input: default@lineitem
http://git-wip-us.apache.org/repos/asf/hive/blob/cc3fd84e/ql/src/test/results/clientpositive/llap/vectorized_dynamic_partition_pruning.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/vectorized_dynamic_partition_pruning.q.out b/ql/src/test/results/clientpositive/llap/vectorized_dynamic_partition_pruning.q.out
index dc1b60f..3d087b3 100644
--- a/ql/src/test/results/clientpositive/llap/vectorized_dynamic_partition_pruning.q.out
+++ b/ql/src/test/results/clientpositive/llap/vectorized_dynamic_partition_pruning.q.out
@@ -2784,6 +2784,21 @@ STAGE PLANS:
sort order: +
Map-reduce partition columns: _col0 (type: string)
Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ keys: _col0 (type: string)
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE
+ Dynamic Partitioning Event Operator
+ Target column: hr (string)
+ Target Input: srcpart
+ Partition key expr: hr
+ Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE
+ Target Vertex: Map 1
Execution mode: vectorized, llap
LLAP IO: all inputs
Reducer 2
@@ -2877,9 +2892,11 @@ STAGE PLANS:
Tez
#### A masked pattern was here ####
Edges:
- Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE)
- Reducer 3 <- Map 6 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE)
+ Map 7 <- Reducer 5 (BROADCAST_EDGE)
+ Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 6 (SIMPLE_EDGE)
+ Reducer 3 <- Map 7 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE)
Reducer 4 <- Reducer 3 (CUSTOM_SIMPLE_EDGE)
+ Reducer 5 <- Reducer 2 (CUSTOM_SIMPLE_EDGE)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -2903,7 +2920,7 @@ STAGE PLANS:
value expressions: _col1 (type: string)
Execution mode: vectorized, llap
LLAP IO: unknown
- Map 5
+ Map 6
Map Operator Tree:
TableScan
alias: srcpart_date
@@ -2923,14 +2940,14 @@ STAGE PLANS:
Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE
Execution mode: vectorized, llap
LLAP IO: all inputs
- Map 6
+ Map 7
Map Operator Tree:
TableScan
alias: srcpart_hour
- filterExpr: (UDFToDouble(hr) = 13.0) (type: boolean)
+ filterExpr: ((UDFToDouble(hr) = 13.0) and hr BETWEEN DynamicValue(RS_12_srcpart_hr_min) AND DynamicValue(RS_12_srcpart_hr_max) and in_bloom_filter(hr, DynamicValue(RS_12_srcpart_hr_bloom_filter))) (type: boolean)
Statistics: Num rows: 2 Data size: 344 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: (UDFToDouble(hr) = 13.0) (type: boolean)
+ predicate: ((UDFToDouble(hr) = 13.0) and hr BETWEEN DynamicValue(RS_12_srcpart_hr_min) AND DynamicValue(RS_12_srcpart_hr_max) and in_bloom_filter(hr, DynamicValue(RS_12_srcpart_hr_bloom_filter))) (type: boolean)
Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: hr (type: string)
@@ -2941,7 +2958,7 @@ STAGE PLANS:
sort order: +
Map-reduce partition columns: _col0 (type: string)
Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE
- Execution mode: vectorized, llap
+ Execution mode: llap
LLAP IO: all inputs
Reducer 2
Execution mode: llap
@@ -2959,6 +2976,19 @@ STAGE PLANS:
sort order: +
Map-reduce partition columns: _col1 (type: string)
Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col1 (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: min(_col0), max(_col0), bloom_filter(_col0, expectedEntries=1)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: binary)
Reducer 3
Execution mode: llap
Reduce Operator Tree:
@@ -2993,6 +3023,18 @@ 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 5
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: min(VALUE._col0), max(VALUE._col1), bloom_filter(VALUE._col2, expectedEntries=1)
+ mode: final
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: binary)
Stage: Stage-0
Fetch Operator
@@ -5036,6 +5078,21 @@ STAGE PLANS:
sort order: +
Map-reduce partition columns: _col0 (type: string)
Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ keys: _col0 (type: string)
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE
+ Dynamic Partitioning Event Operator
+ Target column: hr (string)
+ Target Input: srcpart
+ Partition key expr: hr
+ Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE
+ Target Vertex: Map 1
Execution mode: vectorized, llap
LLAP IO: all inputs
Reducer 2
http://git-wip-us.apache.org/repos/asf/hive/blob/cc3fd84e/ql/src/test/results/clientpositive/perf/query16.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/perf/query16.q.out b/ql/src/test/results/clientpositive/perf/query16.q.out
index 1648ddb..1be5fba 100644
--- a/ql/src/test/results/clientpositive/perf/query16.q.out
+++ b/ql/src/test/results/clientpositive/perf/query16.q.out
@@ -1,5 +1,5 @@
Warning: Shuffle Join MERGEJOIN[141][tables = [$hdt$_2, $hdt$_3, $hdt$_1, $hdt$_4]] in Stage 'Reducer 13' is a cross product
-Warning: Shuffle Join MERGEJOIN[143][tables = [$hdt$_2, $hdt$_3, $hdt$_1, $hdt$_4]] in Stage 'Reducer 25' is a cross product
+Warning: Shuffle Join MERGEJOIN[142][tables = [$hdt$_2, $hdt$_3, $hdt$_1, $hdt$_4]] in Stage 'Reducer 25' is a cross product
PREHOOK: query: explain select
count(distinct cs_order_number) as `order count`
,sum(cs_ext_ship_cost) as `total shipping cost`
@@ -117,7 +117,7 @@ Stage-0
Output:["_col2","_col3"]
Filter Operator [FIL_63] (rows=5072854730221289472 width=1)
predicate:(_col2 <> _col0)
- Merge Join Operator [MERGEJOIN_144] (rows=5072854730221289472 width=1)
+ Merge Join Operator [MERGEJOIN_147] (rows=5072854730221289472 width=1)
Conds:RS_60._col1=RS_61._col1(Inner),Output:["_col0","_col2","_col3"]
<-Map 21 [SIMPLE_EDGE]
SHUFFLE [RS_60]
@@ -140,7 +140,7 @@ Stage-0
Output:["_col0","_col1"],keys:_col4, _col3
Select Operator [SEL_55] (rows=9223372036854775807 width=1)
Output:["_col4","_col3"]
- Merge Join Operator [MERGEJOIN_143] (rows=9223372036854775807 width=1)
+ Merge Join Operator [MERGEJOIN_142] (rows=9223372036854775807 width=1)
Conds:(Inner),(Inner),(Inner),Output:["_col3","_col4"]
<-Map 24 [CUSTOM_SIMPLE_EDGE]
PARTITION_ONLY_SHUFFLE [RS_50]
@@ -180,7 +180,7 @@ Stage-0
PartitionCols:_col0
Group By Operator [GBY_36] (rows=5072854730221289472 width=1)
Output:["_col0"],keys:_col0
- Merge Join Operator [MERGEJOIN_142] (rows=5072854730221289472 width=1)
+ Merge Join Operator [MERGEJOIN_146] (rows=5072854730221289472 width=1)
Conds:RS_32._col0=RS_33._col0(Inner),Output:["_col0"]
<-Map 20 [SIMPLE_EDGE]
SHUFFLE [RS_33]
@@ -225,7 +225,7 @@ Stage-0
<-Reducer 4 [SIMPLE_EDGE]
SHUFFLE [RS_78]
PartitionCols:_col4
- Merge Join Operator [MERGEJOIN_147] (rows=383314495 width=135)
+ Merge Join Operator [MERGEJOIN_145] (rows=383314495 width=135)
Conds:RS_75._col2=RS_76._col0(Inner),Output:["_col3","_col4","_col5","_col6"]
<-Map 11 [SIMPLE_EDGE]
SHUFFLE [RS_76]
@@ -239,7 +239,7 @@ Stage-0
<-Reducer 3 [SIMPLE_EDGE]
SHUFFLE [RS_75]
PartitionCols:_col2
- Merge Join Operator [MERGEJOIN_146] (rows=348467716 width=135)
+ Merge Join Operator [MERGEJOIN_144] (rows=348467716 width=135)
Conds:RS_72._col1=RS_73._col0(Inner),Output:["_col2","_col3","_col4","_col5","_col6"]
<-Map 10 [SIMPLE_EDGE]
SHUFFLE [RS_73]
@@ -253,7 +253,7 @@ Stage-0
<-Reducer 2 [SIMPLE_EDGE]
SHUFFLE [RS_72]
PartitionCols:_col1
- Merge Join Operator [MERGEJOIN_145] (rows=316788826 width=135)
+ Merge Join Operator [MERGEJOIN_143] (rows=316788826 width=135)
Conds:RS_69._col0=RS_70._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5","_col6"]
<-Map 1 [SIMPLE_EDGE]
SHUFFLE [RS_69]
http://git-wip-us.apache.org/repos/asf/hive/blob/cc3fd84e/ql/src/test/results/clientpositive/perf/query6.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/perf/query6.q.out b/ql/src/test/results/clientpositive/perf/query6.q.out
index 5500e7a..094459e 100644
--- a/ql/src/test/results/clientpositive/perf/query6.q.out
+++ b/ql/src/test/results/clientpositive/perf/query6.q.out
@@ -1,4 +1,4 @@
-Warning: Shuffle Join MERGEJOIN[197][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product
+Warning: Shuffle Join MERGEJOIN[196][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product
Warning: Shuffle Join MERGEJOIN[193][tables = [$hdt$_5, $hdt$_6]] in Stage 'Reducer 21' is a cross product
Warning: Shuffle Join MERGEJOIN[194][tables = [$hdt$_5, $hdt$_6, $hdt$_7]] in Stage 'Reducer 22' is a cross product
Warning: Shuffle Join MERGEJOIN[195][tables = [$hdt$_5, $hdt$_6, $hdt$_7, $hdt$_8, $hdt$_9, $hdt$_10, $hdt$_11]] in Stage 'Reducer 23' is a cross product
@@ -160,7 +160,7 @@ Stage-0
Output:["_col0","_col1"],aggregations:["avg(_col0)"],keys:_col2
Select Operator [SEL_87] (rows=5072854730221289472 width=1)
Output:["_col2","_col0"]
- Merge Join Operator [MERGEJOIN_196] (rows=5072854730221289472 width=1)
+ Merge Join Operator [MERGEJOIN_198] (rows=5072854730221289472 width=1)
Conds:RS_84._col1=RS_85._col0(Inner),Output:["_col0","_col2"]
<-Map 17 [SIMPLE_EDGE]
SHUFFLE [RS_84]
@@ -264,7 +264,7 @@ Stage-0
<-Reducer 12 [SIMPLE_EDGE]
SHUFFLE [RS_110]
PartitionCols:_col0
- Merge Join Operator [MERGEJOIN_198] (rows=80353 width=1119)
+ Merge Join Operator [MERGEJOIN_197] (rows=80353 width=1119)
Conds:RS_27._col1=RS_28._col0(Inner),Output:["_col0"]
<-Map 11 [SIMPLE_EDGE]
SHUFFLE [RS_27]
@@ -294,7 +294,7 @@ Stage-0
<-Reducer 2 [SIMPLE_EDGE]
SHUFFLE [RS_109]
PartitionCols:_col0
- Merge Join Operator [MERGEJOIN_197] (rows=575995635 width=97)
+ Merge Join Operator [MERGEJOIN_196] (rows=575995635 width=97)
Conds:(Inner),Output:["_col0","_col1","_col2"]
<-Map 1 [CUSTOM_SIMPLE_EDGE]
PARTITION_ONLY_SHUFFLE [RS_106]