http://git-wip-us.apache.org/repos/asf/hive/blob/55887646/ql/src/test/results/clientpositive/llap/tez_dynpart_hashjoin_2.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/tez_dynpart_hashjoin_2.q.out b/ql/src/test/results/clientpositive/llap/tez_dynpart_hashjoin_2.q.out index 37970ab..7e09d5e 100644 --- a/ql/src/test/results/clientpositive/llap/tez_dynpart_hashjoin_2.q.out +++ b/ql/src/test/results/clientpositive/llap/tez_dynpart_hashjoin_2.q.out @@ -51,14 +51,14 @@ STAGE PLANS: predicate: (csmallint < 100S) (type: boolean) Statistics: Num rows: 4096 Data size: 1031250 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: ctinyint (type: tinyint), csmallint (type: smallint), cint (type: int), cbigint (type: bigint), cfloat (type: float), cdouble (type: double), cstring1 (type: string), cstring2 (type: string), ctimestamp1 (type: timestamp), ctimestamp2 (type: timestamp), cboolean1 (type: boolean), cboolean2 (type: boolean) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 - Statistics: Num rows: 4096 Data size: 1031250 Basic stats: COMPLETE Column stats: COMPLETE + expressions: ctinyint (type: tinyint), csmallint (type: smallint), cint (type: int), cbigint (type: bigint), cfloat (type: float), cdouble (type: double), cstring1 (type: string), cstring2 (type: string), ctimestamp1 (type: timestamp), ctimestamp2 (type: timestamp), cboolean1 (type: boolean), cboolean2 (type: boolean), UDFToInteger(csmallint) (type: int) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 + Statistics: Num rows: 4096 Data size: 1043486 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator - key expressions: UDFToInteger(_col1) (type: int) + key expressions: _col12 (type: int) sort order: + - Map-reduce partition columns: UDFToInteger(_col1) (type: int) - Statistics: Num rows: 4096 Data size: 1031250 Basic stats: COMPLETE Column stats: COMPLETE + Map-reduce partition columns: _col12 (type: int) + Statistics: Num rows: 4096 Data size: 1043486 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: tinyint), _col1 (type: smallint), _col2 (type: int), _col3 (type: bigint), _col4 (type: float), _col5 (type: double), _col6 (type: string), _col7 (type: string), _col8 (type: timestamp), _col9 (type: timestamp), _col10 (type: boolean), _col11 (type: boolean) Execution mode: vectorized, llap LLAP IO: all inputs @@ -72,14 +72,14 @@ STAGE PLANS: 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) + expressions: UDFToInteger(key) (type: int) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator - key expressions: UDFToInteger(_col0) (type: int) + key expressions: _col0 (type: int) sort order: + - Map-reduce partition columns: UDFToInteger(_col0) (type: int) - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: no inputs Map 5 @@ -92,14 +92,14 @@ STAGE PLANS: 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) + expressions: (UDFToInteger(key) + 0) (type: int) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator - key expressions: (UDFToInteger(_col0) + 0) (type: int) + key expressions: _col0 (type: int) sort order: + - Map-reduce partition columns: (UDFToInteger(_col0) + 0) (type: int) - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: no inputs Reducer 2 @@ -110,9 +110,9 @@ STAGE PLANS: Inner Join 0 to 1 Inner Join 0 to 2 keys: - 0 UDFToInteger(_col1) (type: int) - 1 UDFToInteger(_col0) (type: int) - 2 (UDFToInteger(_col0) + 0) (type: int) + 0 _col12 (type: int) + 1 _col0 (type: int) + 2 _col0 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 Statistics: Num rows: 791 Data size: 6700 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator @@ -251,14 +251,14 @@ STAGE PLANS: predicate: (csmallint < 100S) (type: boolean) Statistics: Num rows: 4096 Data size: 1031250 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: ctinyint (type: tinyint), csmallint (type: smallint), cint (type: int), cbigint (type: bigint), cfloat (type: float), cdouble (type: double), cstring1 (type: string), cstring2 (type: string), ctimestamp1 (type: timestamp), ctimestamp2 (type: timestamp), cboolean1 (type: boolean), cboolean2 (type: boolean) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 - Statistics: Num rows: 4096 Data size: 1031250 Basic stats: COMPLETE Column stats: COMPLETE + expressions: ctinyint (type: tinyint), csmallint (type: smallint), cint (type: int), cbigint (type: bigint), cfloat (type: float), cdouble (type: double), cstring1 (type: string), cstring2 (type: string), ctimestamp1 (type: timestamp), ctimestamp2 (type: timestamp), cboolean1 (type: boolean), cboolean2 (type: boolean), UDFToInteger(csmallint) (type: int) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 + Statistics: Num rows: 4096 Data size: 1043486 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator - key expressions: UDFToInteger(_col1) (type: int) + key expressions: _col12 (type: int) sort order: + - Map-reduce partition columns: UDFToInteger(_col1) (type: int) - Statistics: Num rows: 4096 Data size: 1031250 Basic stats: COMPLETE Column stats: COMPLETE + Map-reduce partition columns: _col12 (type: int) + Statistics: Num rows: 4096 Data size: 1043486 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: tinyint), _col1 (type: smallint), _col2 (type: int), _col3 (type: bigint), _col4 (type: float), _col5 (type: double), _col6 (type: string), _col7 (type: string), _col8 (type: timestamp), _col9 (type: timestamp), _col10 (type: boolean), _col11 (type: boolean) Execution mode: vectorized, llap LLAP IO: all inputs @@ -272,14 +272,14 @@ STAGE PLANS: 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) + expressions: UDFToInteger(key) (type: int) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator - key expressions: UDFToInteger(_col0) (type: int) + key expressions: _col0 (type: int) sort order: + - Map-reduce partition columns: UDFToInteger(_col0) (type: int) - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: no inputs Map 5 @@ -292,14 +292,14 @@ STAGE PLANS: 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) + expressions: (UDFToInteger(key) + 0) (type: int) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator - key expressions: (UDFToInteger(_col0) + 0) (type: int) + key expressions: _col0 (type: int) sort order: + - Map-reduce partition columns: (UDFToInteger(_col0) + 0) (type: int) - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: no inputs Reducer 2 @@ -310,9 +310,9 @@ STAGE PLANS: Inner Join 0 to 1 Inner Join 0 to 2 keys: - 0 UDFToInteger(_col1) (type: int) - 1 UDFToInteger(_col0) (type: int) - 2 (UDFToInteger(_col0) + 0) (type: int) + 0 _col12 (type: int) + 1 _col0 (type: int) + 2 _col0 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 Statistics: Num rows: 791 Data size: 6700 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator @@ -451,14 +451,14 @@ STAGE PLANS: predicate: (csmallint < 100S) (type: boolean) Statistics: Num rows: 4096 Data size: 1031250 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: ctinyint (type: tinyint), csmallint (type: smallint), cint (type: int), cbigint (type: bigint), cfloat (type: float), cdouble (type: double), cstring1 (type: string), cstring2 (type: string), ctimestamp1 (type: timestamp), ctimestamp2 (type: timestamp), cboolean1 (type: boolean), cboolean2 (type: boolean) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 - Statistics: Num rows: 4096 Data size: 1031250 Basic stats: COMPLETE Column stats: COMPLETE + expressions: ctinyint (type: tinyint), csmallint (type: smallint), cint (type: int), cbigint (type: bigint), cfloat (type: float), cdouble (type: double), cstring1 (type: string), cstring2 (type: string), ctimestamp1 (type: timestamp), ctimestamp2 (type: timestamp), cboolean1 (type: boolean), cboolean2 (type: boolean), UDFToInteger(csmallint) (type: int) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 + Statistics: Num rows: 4096 Data size: 1043486 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator - key expressions: UDFToInteger(_col1) (type: int) + key expressions: _col12 (type: int) sort order: + - Map-reduce partition columns: UDFToInteger(_col1) (type: int) - Statistics: Num rows: 4096 Data size: 1031250 Basic stats: COMPLETE Column stats: COMPLETE + Map-reduce partition columns: _col12 (type: int) + Statistics: Num rows: 4096 Data size: 1043486 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: tinyint), _col1 (type: smallint), _col2 (type: int), _col3 (type: bigint), _col4 (type: float), _col5 (type: double), _col6 (type: string), _col7 (type: string), _col8 (type: timestamp), _col9 (type: timestamp), _col10 (type: boolean), _col11 (type: boolean) Execution mode: vectorized, llap LLAP IO: all inputs @@ -472,14 +472,14 @@ STAGE PLANS: 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) + expressions: UDFToInteger(key) (type: int) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator - key expressions: UDFToInteger(_col0) (type: int) + key expressions: _col0 (type: int) sort order: + - Map-reduce partition columns: UDFToInteger(_col0) (type: int) - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: no inputs Map 5 @@ -492,14 +492,14 @@ STAGE PLANS: 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) + expressions: (UDFToInteger(key) + 0) (type: int) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator - key expressions: (UDFToInteger(_col0) + 0) (type: int) + key expressions: _col0 (type: int) sort order: + - Map-reduce partition columns: (UDFToInteger(_col0) + 0) (type: int) - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: no inputs Reducer 2 @@ -510,9 +510,9 @@ STAGE PLANS: Inner Join 0 to 1 Inner Join 0 to 2 keys: - 0 UDFToInteger(_col1) (type: int) - 1 UDFToInteger(_col0) (type: int) - 2 (UDFToInteger(_col0) + 0) (type: int) + 0 _col12 (type: int) + 1 _col0 (type: int) + 2 _col0 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 Statistics: Num rows: 791 Data size: 6700 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator
http://git-wip-us.apache.org/repos/asf/hive/blob/55887646/ql/src/test/results/clientpositive/llap/tez_dynpart_hashjoin_3.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/tez_dynpart_hashjoin_3.q.out b/ql/src/test/results/clientpositive/llap/tez_dynpart_hashjoin_3.q.out index 3a0d0a9..8caf6c7 100644 --- a/ql/src/test/results/clientpositive/llap/tez_dynpart_hashjoin_3.q.out +++ b/ql/src/test/results/clientpositive/llap/tez_dynpart_hashjoin_3.q.out @@ -35,17 +35,17 @@ STAGE PLANS: alias: a Statistics: Num rows: 12288 Data size: 3093170 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: ctinyint (type: tinyint), csmallint (type: smallint), cint (type: int), cbigint (type: bigint), cfloat (type: float), cdouble (type: double), cstring1 (type: string), cstring2 (type: string), ctimestamp1 (type: timestamp), ctimestamp2 (type: timestamp), cboolean1 (type: boolean), cboolean2 (type: boolean) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 - Statistics: Num rows: 12288 Data size: 3093170 Basic stats: COMPLETE Column stats: COMPLETE + expressions: ctinyint (type: tinyint), csmallint (type: smallint), cint (type: int), cbigint (type: bigint), cfloat (type: float), cdouble (type: double), cstring1 (type: string), cstring2 (type: string), ctimestamp1 (type: timestamp), ctimestamp2 (type: timestamp), cboolean1 (type: boolean), cboolean2 (type: boolean), (cint < 100) (type: boolean) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 + Statistics: Num rows: 12288 Data size: 3142322 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 1 - Statistics: Num rows: 1 Data size: 310 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 314 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 310 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 314 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 - value expressions: _col0 (type: tinyint), _col1 (type: smallint), _col2 (type: int), _col3 (type: bigint), _col4 (type: float), _col5 (type: double), _col6 (type: string), _col7 (type: string), _col8 (type: timestamp), _col9 (type: timestamp), _col10 (type: boolean), _col11 (type: boolean) + value expressions: _col0 (type: tinyint), _col1 (type: smallint), _col2 (type: int), _col3 (type: bigint), _col4 (type: float), _col5 (type: double), _col6 (type: string), _col7 (type: string), _col8 (type: timestamp), _col9 (type: timestamp), _col10 (type: boolean), _col11 (type: boolean), _col12 (type: boolean) Execution mode: vectorized, llap LLAP IO: all inputs Map 4 @@ -54,32 +54,32 @@ STAGE PLANS: alias: b Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: key (type: string) + expressions: UDFToInteger(key) (type: int) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator - key expressions: UDFToInteger(_col0) (type: int) + key expressions: _col0 (type: int) sort order: + - Map-reduce partition columns: UDFToInteger(_col0) (type: int) - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: no inputs Reducer 2 Execution mode: vectorized, llap Reduce Operator Tree: Select Operator - expressions: VALUE._col0 (type: tinyint), VALUE._col1 (type: smallint), VALUE._col2 (type: int), VALUE._col3 (type: bigint), VALUE._col4 (type: float), VALUE._col5 (type: double), VALUE._col6 (type: string), VALUE._col7 (type: string), VALUE._col8 (type: timestamp), VALUE._col9 (type: timestamp), VALUE._col10 (type: boolean), VALUE._col11 (type: boolean) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 - Statistics: Num rows: 1 Data size: 310 Basic stats: COMPLETE Column stats: COMPLETE + expressions: VALUE._col0 (type: tinyint), VALUE._col1 (type: smallint), VALUE._col2 (type: int), VALUE._col3 (type: bigint), VALUE._col4 (type: float), VALUE._col5 (type: double), VALUE._col6 (type: string), VALUE._col7 (type: string), VALUE._col8 (type: timestamp), VALUE._col9 (type: timestamp), VALUE._col10 (type: boolean), VALUE._col11 (type: boolean), VALUE._col12 (type: boolean) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 + Statistics: Num rows: 1 Data size: 314 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 1 - Statistics: Num rows: 1 Data size: 310 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 314 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col2 (type: int) sort order: + Map-reduce partition columns: _col2 (type: int) - Statistics: Num rows: 1 Data size: 310 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: tinyint), _col1 (type: smallint), _col3 (type: bigint), _col4 (type: float), _col5 (type: double), _col6 (type: string), _col7 (type: string), _col8 (type: timestamp), _col9 (type: timestamp), _col10 (type: boolean), _col11 (type: boolean) + Statistics: Num rows: 1 Data size: 314 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: tinyint), _col1 (type: smallint), _col3 (type: bigint), _col4 (type: float), _col5 (type: double), _col6 (type: string), _col7 (type: string), _col8 (type: timestamp), _col9 (type: timestamp), _col10 (type: boolean), _col11 (type: boolean), _col12 (type: boolean) Reducer 3 Execution mode: llap Reduce Operator Tree: @@ -87,11 +87,11 @@ STAGE PLANS: condition map: Left Outer Join 0 to 1 filter predicates: - 0 {(KEY.reducesinkkey0 < 100)} + 0 {VALUE._col11} 1 keys: 0 _col2 (type: int) - 1 UDFToInteger(_col0) (type: int) + 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 Statistics: Num rows: 2 Data size: 620 Basic stats: COMPLETE Column stats: COMPLETE Limit @@ -138,8 +138,7 @@ STAGE PLANS: Tez #### A masked pattern was here #### Edges: - Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE) - Reducer 3 <- Map 4 (CUSTOM_SIMPLE_EDGE), Reducer 2 (CUSTOM_SIMPLE_EDGE) + Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE), Map 3 (BROADCAST_EDGE) #### A masked pattern was here #### Vertices: Map 1 @@ -148,79 +147,68 @@ STAGE PLANS: alias: a Statistics: Num rows: 12288 Data size: 3093170 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: ctinyint (type: tinyint), csmallint (type: smallint), cint (type: int), cbigint (type: bigint), cfloat (type: float), cdouble (type: double), cstring1 (type: string), cstring2 (type: string), ctimestamp1 (type: timestamp), ctimestamp2 (type: timestamp), cboolean1 (type: boolean), cboolean2 (type: boolean) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 - Statistics: Num rows: 12288 Data size: 3093170 Basic stats: COMPLETE Column stats: COMPLETE + expressions: ctinyint (type: tinyint), csmallint (type: smallint), cint (type: int), cbigint (type: bigint), cfloat (type: float), cdouble (type: double), cstring1 (type: string), cstring2 (type: string), ctimestamp1 (type: timestamp), ctimestamp2 (type: timestamp), cboolean1 (type: boolean), cboolean2 (type: boolean), (cint < 100) (type: boolean) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 + Statistics: Num rows: 12288 Data size: 3142322 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 1 - Statistics: Num rows: 1 Data size: 310 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 314 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 310 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 314 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 - value expressions: _col0 (type: tinyint), _col1 (type: smallint), _col2 (type: int), _col3 (type: bigint), _col4 (type: float), _col5 (type: double), _col6 (type: string), _col7 (type: string), _col8 (type: timestamp), _col9 (type: timestamp), _col10 (type: boolean), _col11 (type: boolean) + value expressions: _col0 (type: tinyint), _col1 (type: smallint), _col2 (type: int), _col3 (type: bigint), _col4 (type: float), _col5 (type: double), _col6 (type: string), _col7 (type: string), _col8 (type: timestamp), _col9 (type: timestamp), _col10 (type: boolean), _col11 (type: boolean), _col12 (type: boolean) Execution mode: vectorized, llap LLAP IO: all inputs - Map 4 + Map 3 Map Operator Tree: TableScan alias: b Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: key (type: string) + expressions: UDFToInteger(key) (type: int) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator - key expressions: UDFToInteger(_col0) (type: int) + key expressions: _col0 (type: int) sort order: + - Map-reduce partition columns: UDFToInteger(_col0) (type: int) - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: no inputs Reducer 2 Execution mode: vectorized, llap Reduce Operator Tree: Select Operator - expressions: VALUE._col0 (type: tinyint), VALUE._col1 (type: smallint), VALUE._col2 (type: int), VALUE._col3 (type: bigint), VALUE._col4 (type: float), VALUE._col5 (type: double), VALUE._col6 (type: string), VALUE._col7 (type: string), VALUE._col8 (type: timestamp), VALUE._col9 (type: timestamp), VALUE._col10 (type: boolean), VALUE._col11 (type: boolean) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 - Statistics: Num rows: 1 Data size: 310 Basic stats: COMPLETE Column stats: COMPLETE + expressions: VALUE._col0 (type: tinyint), VALUE._col1 (type: smallint), VALUE._col2 (type: int), VALUE._col3 (type: bigint), VALUE._col4 (type: float), VALUE._col5 (type: double), VALUE._col6 (type: string), VALUE._col7 (type: string), VALUE._col8 (type: timestamp), VALUE._col9 (type: timestamp), VALUE._col10 (type: boolean), VALUE._col11 (type: boolean), VALUE._col12 (type: boolean) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 + Statistics: Num rows: 1 Data size: 314 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 1 - Statistics: Num rows: 1 Data size: 310 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col2 (type: int) - sort order: + - Map-reduce partition columns: _col2 (type: int) - Statistics: Num rows: 1 Data size: 310 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: tinyint), _col1 (type: smallint), _col3 (type: bigint), _col4 (type: float), _col5 (type: double), _col6 (type: string), _col7 (type: string), _col8 (type: timestamp), _col9 (type: timestamp), _col10 (type: boolean), _col11 (type: boolean) - Reducer 3 - Execution mode: vectorized, llap - Reduce Operator Tree: - Map Join Operator - condition map: - Left Outer Join 0 to 1 - filter predicates: - 0 {(KEY.reducesinkkey0 < 100)} - 1 - keys: - 0 KEY.reducesinkkey0 (type: int) - 1 KEY.reducesinkkey0 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 - input vertices: - 1 Map 4 - Statistics: Num rows: 2 Data size: 620 Basic stats: COMPLETE Column stats: COMPLETE - DynamicPartitionHashJoin: true - HybridGraceHashJoin: true - Limit - Number of rows: 1 - Statistics: Num rows: 1 Data size: 310 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 310 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 + Statistics: Num rows: 1 Data size: 314 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Left Outer Join 0 to 1 + filter predicates: + 0 {_col12} + 1 + keys: + 0 _col2 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 + input vertices: + 1 Map 3 + Statistics: Num rows: 2 Data size: 620 Basic stats: COMPLETE Column stats: COMPLETE + Limit + Number of rows: 1 + Statistics: Num rows: 1 Data size: 310 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 310 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -255,8 +243,7 @@ STAGE PLANS: Tez #### A masked pattern was here #### Edges: - Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE) - Reducer 3 <- Map 4 (CUSTOM_SIMPLE_EDGE), Reducer 2 (CUSTOM_SIMPLE_EDGE) + Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE), Map 3 (BROADCAST_EDGE) #### A masked pattern was here #### Vertices: Map 1 @@ -278,20 +265,20 @@ STAGE PLANS: value expressions: _col0 (type: tinyint), _col1 (type: smallint), _col2 (type: int), _col3 (type: bigint), _col4 (type: float), _col5 (type: double), _col6 (type: string), _col7 (type: string), _col8 (type: timestamp), _col9 (type: timestamp), _col10 (type: boolean), _col11 (type: boolean) Execution mode: vectorized, llap LLAP IO: all inputs - Map 4 + Map 3 Map Operator Tree: TableScan alias: b Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: key (type: string) + expressions: UDFToInteger(key) (type: int) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator - key expressions: UDFToInteger(_col0) (type: int) + key expressions: _col0 (type: int) sort order: + - Map-reduce partition columns: UDFToInteger(_col0) (type: int) - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: no inputs Reducer 2 @@ -304,37 +291,26 @@ STAGE PLANS: Limit Number of rows: 1 Statistics: Num rows: 1 Data size: 310 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col2 (type: int) - sort order: + - Map-reduce partition columns: _col2 (type: int) - Statistics: Num rows: 1 Data size: 310 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: tinyint), _col1 (type: smallint), _col3 (type: bigint), _col4 (type: float), _col5 (type: double), _col6 (type: string), _col7 (type: string), _col8 (type: timestamp), _col9 (type: timestamp), _col10 (type: boolean), _col11 (type: boolean) - Reducer 3 - Execution mode: vectorized, llap - Reduce Operator Tree: - Map Join Operator - condition map: - Left Outer Join 0 to 1 - keys: - 0 KEY.reducesinkkey0 (type: int) - 1 KEY.reducesinkkey0 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 - input vertices: - 1 Map 4 - Statistics: Num rows: 2 Data size: 620 Basic stats: COMPLETE Column stats: COMPLETE - DynamicPartitionHashJoin: true - HybridGraceHashJoin: true - Limit - Number of rows: 1 - Statistics: Num rows: 1 Data size: 310 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 310 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 + Map Join Operator + condition map: + Left Outer Join 0 to 1 + keys: + 0 _col2 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 + input vertices: + 1 Map 3 + Statistics: Num rows: 2 Data size: 620 Basic stats: COMPLETE Column stats: COMPLETE + Limit + Number of rows: 1 + Statistics: Num rows: 1 Data size: 310 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 310 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator http://git-wip-us.apache.org/repos/asf/hive/blob/55887646/ql/src/test/results/clientpositive/llap/tez_fixed_bucket_pruning.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/tez_fixed_bucket_pruning.q.out b/ql/src/test/results/clientpositive/llap/tez_fixed_bucket_pruning.q.out index 76fe6ea..1574565 100644 --- a/ql/src/test/results/clientpositive/llap/tez_fixed_bucket_pruning.q.out +++ b/ql/src/test/results/clientpositive/llap/tez_fixed_bucket_pruning.q.out @@ -465,16 +465,16 @@ POSTHOOK: Input: default@l3_monthly_dw_dimplan #### A masked pattern was here #### OPTIMIZED SQL: SELECT CAST(7147200 AS BIGINT) AS `project_object_id`, `t9`.`plan_key`, `t9`.`project_key` FROM (SELECT `t4`.`plan_key`, `t6`.`project_key` -FROM (SELECT `t3`.`l3_snapshot_number`, `t2`.`plan_detail_object_id`, `t2`.`project_object_id`, `t0`.`idp_data_date`, `t0`.`l3_snapshot_number` AS `l3_snapshot_number0`, `t0`.`plan_key`, `t0`.`finplan_detail_object_id` -FROM (SELECT CAST(DATE '2017-12-28' AS DATE) AS `idp_data_date`, `l3_snapshot_number`, `plan_key`, `finplan_detail_object_id` +FROM (SELECT `t3`.`l3_snapshot_number`, `t2`.`plan_detail_object_id`, `t0`.`l3_snapshot_number` AS `l3_snapshot_number0`, `t0`.`plan_key`, `t0`.`finplan_detail_object_id` +FROM (SELECT `l3_snapshot_number`, `plan_key`, `finplan_detail_object_id` FROM `default`.`l3_monthly_dw_dimplan` WHERE `idp_data_date` = DATE '2017-12-28') AS `t0` -RIGHT JOIN ((SELECT `plan_detail_object_id`, CAST(7147200 AS BIGINT) AS `project_object_id` +RIGHT JOIN ((SELECT `plan_detail_object_id` FROM `default`.`l3_clarity__l3_monthly_dw_factplan_dw_stg_2018022300104_1` WHERE `project_object_id` = 7147200) AS `t2`, (SELECT `l3_snapshot_number` FROM `default`.`l3_clarity__l3_snap_number_2018022300104`) AS `t3`) ON `t0`.`finplan_detail_object_id` = `t2`.`plan_detail_object_id` AND `t0`.`l3_snapshot_number` = `t3`.`l3_snapshot_number`) AS `t4` -LEFT JOIN (SELECT `project_key`, `l3_snapshot_number`, CAST(7147200 AS BIGINT) AS `project_object_id`, CAST(DATE '2017-12-28' AS DATE) AS `idp_data_date` +LEFT JOIN (SELECT `project_key`, `l3_snapshot_number` FROM `default`.`l3_clarity__l3_monthly_dw_factplan_datajoin_1_s2_2018022300104_1` WHERE `idp_data_date` = DATE '2017-12-28' AND `project_object_id` = 7147200) AS `t6` ON `t4`.`l3_snapshot_number` = `t6`.`l3_snapshot_number` ORDER BY `t4`.`plan_key`, `t6`.`project_key` @@ -506,7 +506,7 @@ STAGE PLANS: Select Operator expressions: plan_detail_object_id (type: bigint) outputColumnNames: _col0 - Statistics: Num rows: 15 Data size: 240 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 15 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -514,7 +514,7 @@ STAGE PLANS: keys: 0 1 - outputColumnNames: _col0, _col2 + outputColumnNames: _col0, _col1 input vertices: 1 Map 3 Position of Big Table: 0 @@ -524,16 +524,16 @@ STAGE PLANS: Left Outer Join 0 to 1 Estimated key counts: Map 4 => 90170 keys: - 0 _col2 (type: bigint), _col0 (type: bigint) - 1 _col1 (type: bigint), _col3 (type: bigint) - outputColumnNames: _col2, _col5 + 0 _col1 (type: bigint), _col0 (type: bigint) + 1 _col0 (type: bigint), _col2 (type: bigint) + outputColumnNames: _col1, _col3 input vertices: 1 Map 4 Position of Big Table: 0 Statistics: Num rows: 30 Data size: 368 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: _col2 (type: bigint), _col5 (type: bigint) - outputColumnNames: _col0, _col5 + expressions: _col1 (type: bigint), _col3 (type: bigint) + outputColumnNames: _col0, _col3 Statistics: Num rows: 30 Data size: 368 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: @@ -542,13 +542,13 @@ STAGE PLANS: keys: 0 _col0 (type: bigint) 1 _col1 (type: bigint) - outputColumnNames: _col5, _col7 + outputColumnNames: _col3, _col5 input vertices: 1 Map 5 Position of Big Table: 0 Statistics: Num rows: 30 Data size: 368 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: _col5 (type: bigint), _col7 (type: bigint) + expressions: _col3 (type: bigint), _col5 (type: bigint) outputColumnNames: _col0, _col1 Statistics: Num rows: 30 Data size: 368 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator @@ -700,16 +700,16 @@ STAGE PLANS: Statistics: Num rows: 90170 Data size: 7213600 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: l3_snapshot_number (type: bigint), plan_key (type: bigint), finplan_detail_object_id (type: bigint) - outputColumnNames: _col1, _col2, _col3 - Statistics: Num rows: 90170 Data size: 7213600 Basic stats: COMPLETE Column stats: COMPLETE + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 90170 Data size: 2164080 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator - key expressions: _col1 (type: bigint), _col3 (type: bigint) + key expressions: _col0 (type: bigint), _col2 (type: bigint) null sort order: aa sort order: ++ - Map-reduce partition columns: _col1 (type: bigint), _col3 (type: bigint) - Statistics: Num rows: 90170 Data size: 7213600 Basic stats: COMPLETE Column stats: COMPLETE + Map-reduce partition columns: _col0 (type: bigint), _col2 (type: bigint) + Statistics: Num rows: 90170 Data size: 2164080 Basic stats: COMPLETE Column stats: COMPLETE tag: 1 - value expressions: _col2 (type: bigint) + value expressions: _col1 (type: bigint) auto parallelism: true Execution mode: vectorized, llap LLAP IO: all inputs @@ -782,13 +782,13 @@ STAGE PLANS: Select Operator expressions: project_key (type: bigint), l3_snapshot_number (type: bigint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 80 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: bigint) null sort order: a sort order: + Map-reduce partition columns: _col1 (type: bigint) - Statistics: Num rows: 1 Data size: 80 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE tag: 1 value expressions: _col0 (type: bigint) auto parallelism: true @@ -974,16 +974,16 @@ POSTHOOK: Input: default@l3_monthly_dw_dimplan #### A masked pattern was here #### OPTIMIZED SQL: SELECT CAST(7147200 AS BIGINT) AS `project_object_id`, `t9`.`plan_key`, `t9`.`project_key` FROM (SELECT `t4`.`plan_key`, `t6`.`project_key` -FROM (SELECT `t3`.`l3_snapshot_number`, `t2`.`plan_detail_object_id`, `t2`.`project_object_id`, `t0`.`idp_data_date`, `t0`.`l3_snapshot_number` AS `l3_snapshot_number0`, `t0`.`plan_key`, `t0`.`finplan_detail_object_id` -FROM (SELECT CAST(DATE '2017-12-28' AS DATE) AS `idp_data_date`, `l3_snapshot_number`, `plan_key`, `finplan_detail_object_id` +FROM (SELECT `t3`.`l3_snapshot_number`, `t2`.`plan_detail_object_id`, `t0`.`l3_snapshot_number` AS `l3_snapshot_number0`, `t0`.`plan_key`, `t0`.`finplan_detail_object_id` +FROM (SELECT `l3_snapshot_number`, `plan_key`, `finplan_detail_object_id` FROM `default`.`l3_monthly_dw_dimplan` WHERE `idp_data_date` = DATE '2017-12-28') AS `t0` -RIGHT JOIN ((SELECT `plan_detail_object_id`, CAST(7147200 AS BIGINT) AS `project_object_id` +RIGHT JOIN ((SELECT `plan_detail_object_id` FROM `default`.`l3_clarity__l3_monthly_dw_factplan_dw_stg_2018022300104_1` WHERE `project_object_id` = 7147200) AS `t2`, (SELECT `l3_snapshot_number` FROM `default`.`l3_clarity__l3_snap_number_2018022300104`) AS `t3`) ON `t0`.`finplan_detail_object_id` = `t2`.`plan_detail_object_id` AND `t0`.`l3_snapshot_number` = `t3`.`l3_snapshot_number`) AS `t4` -LEFT JOIN (SELECT `project_key`, `l3_snapshot_number`, CAST(7147200 AS BIGINT) AS `project_object_id`, CAST(DATE '2017-12-28' AS DATE) AS `idp_data_date` +LEFT JOIN (SELECT `project_key`, `l3_snapshot_number` FROM `default`.`l3_clarity__l3_monthly_dw_factplan_datajoin_1_s2_2018022300104_1` WHERE `idp_data_date` = DATE '2017-12-28' AND `project_object_id` = 7147200) AS `t6` ON `t4`.`l3_snapshot_number` = `t6`.`l3_snapshot_number` ORDER BY `t4`.`plan_key`, `t6`.`project_key` @@ -1015,7 +1015,7 @@ STAGE PLANS: Select Operator expressions: plan_detail_object_id (type: bigint) outputColumnNames: _col0 - Statistics: Num rows: 15 Data size: 240 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 15 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -1023,7 +1023,7 @@ STAGE PLANS: keys: 0 1 - outputColumnNames: _col0, _col2 + outputColumnNames: _col0, _col1 input vertices: 1 Map 3 Position of Big Table: 0 @@ -1033,16 +1033,16 @@ STAGE PLANS: Left Outer Join 0 to 1 Estimated key counts: Map 4 => 90170 keys: - 0 _col2 (type: bigint), _col0 (type: bigint) - 1 _col1 (type: bigint), _col3 (type: bigint) - outputColumnNames: _col2, _col5 + 0 _col1 (type: bigint), _col0 (type: bigint) + 1 _col0 (type: bigint), _col2 (type: bigint) + outputColumnNames: _col1, _col3 input vertices: 1 Map 4 Position of Big Table: 0 Statistics: Num rows: 30 Data size: 368 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: _col2 (type: bigint), _col5 (type: bigint) - outputColumnNames: _col0, _col5 + expressions: _col1 (type: bigint), _col3 (type: bigint) + outputColumnNames: _col0, _col3 Statistics: Num rows: 30 Data size: 368 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: @@ -1051,13 +1051,13 @@ STAGE PLANS: keys: 0 _col0 (type: bigint) 1 _col1 (type: bigint) - outputColumnNames: _col5, _col7 + outputColumnNames: _col3, _col5 input vertices: 1 Map 5 Position of Big Table: 0 Statistics: Num rows: 30 Data size: 368 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: _col5 (type: bigint), _col7 (type: bigint) + expressions: _col3 (type: bigint), _col5 (type: bigint) outputColumnNames: _col0, _col1 Statistics: Num rows: 30 Data size: 368 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator @@ -1210,16 +1210,16 @@ STAGE PLANS: Statistics: Num rows: 90170 Data size: 7213600 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: l3_snapshot_number (type: bigint), plan_key (type: bigint), finplan_detail_object_id (type: bigint) - outputColumnNames: _col1, _col2, _col3 - Statistics: Num rows: 90170 Data size: 7213600 Basic stats: COMPLETE Column stats: COMPLETE + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 90170 Data size: 2164080 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator - key expressions: _col1 (type: bigint), _col3 (type: bigint) + key expressions: _col0 (type: bigint), _col2 (type: bigint) null sort order: aa sort order: ++ - Map-reduce partition columns: _col1 (type: bigint), _col3 (type: bigint) - Statistics: Num rows: 90170 Data size: 7213600 Basic stats: COMPLETE Column stats: COMPLETE + Map-reduce partition columns: _col0 (type: bigint), _col2 (type: bigint) + Statistics: Num rows: 90170 Data size: 2164080 Basic stats: COMPLETE Column stats: COMPLETE tag: 1 - value expressions: _col2 (type: bigint) + value expressions: _col1 (type: bigint) auto parallelism: true Execution mode: vectorized, llap LLAP IO: all inputs @@ -1292,13 +1292,13 @@ STAGE PLANS: Select Operator expressions: project_key (type: bigint), l3_snapshot_number (type: bigint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 80 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: bigint) null sort order: a sort order: + Map-reduce partition columns: _col1 (type: bigint) - Statistics: Num rows: 1 Data size: 80 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE tag: 1 value expressions: _col0 (type: bigint) auto parallelism: true http://git-wip-us.apache.org/repos/asf/hive/blob/55887646/ql/src/test/results/clientpositive/llap/tez_self_join.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/tez_self_join.q.out b/ql/src/test/results/clientpositive/llap/tez_self_join.q.out index c8bde87..fafd5b8 100644 --- a/ql/src/test/results/clientpositive/llap/tez_self_join.q.out +++ b/ql/src/test/results/clientpositive/llap/tez_self_join.q.out @@ -115,14 +115,14 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 176 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: id1 (type: int), id3 (type: string) - outputColumnNames: _col0, _col2 - Statistics: Num rows: 1 Data size: 176 Basic stats: COMPLETE Column stats: COMPLETE + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 90 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 176 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col2 (type: string) + Statistics: Num rows: 1 Data size: 90 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: string) Execution mode: vectorized, llap LLAP IO: no inputs Map 5 @@ -150,12 +150,12 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 _col0 (type: int) - outputColumnNames: _col3 + outputColumnNames: _col2 Statistics: Num rows: 1 Data size: 86 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: Statistics: Num rows: 1 Data size: 86 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col3 (type: string) + value expressions: _col2 (type: string) Reducer 3 Execution mode: llap Reduce Operator Tree: @@ -165,10 +165,10 @@ STAGE PLANS: keys: 0 1 - outputColumnNames: _col3 + outputColumnNames: _col2 Statistics: Num rows: 1 Data size: 86 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: 'ab' (type: string), _col3 (type: string) + expressions: 'ab' (type: string), _col2 (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator http://git-wip-us.apache.org/repos/asf/hive/blob/55887646/ql/src/test/results/clientpositive/llap/tez_vector_dynpart_hashjoin_2.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/tez_vector_dynpart_hashjoin_2.q.out b/ql/src/test/results/clientpositive/llap/tez_vector_dynpart_hashjoin_2.q.out index 37970ab..7e09d5e 100644 --- a/ql/src/test/results/clientpositive/llap/tez_vector_dynpart_hashjoin_2.q.out +++ b/ql/src/test/results/clientpositive/llap/tez_vector_dynpart_hashjoin_2.q.out @@ -51,14 +51,14 @@ STAGE PLANS: predicate: (csmallint < 100S) (type: boolean) Statistics: Num rows: 4096 Data size: 1031250 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: ctinyint (type: tinyint), csmallint (type: smallint), cint (type: int), cbigint (type: bigint), cfloat (type: float), cdouble (type: double), cstring1 (type: string), cstring2 (type: string), ctimestamp1 (type: timestamp), ctimestamp2 (type: timestamp), cboolean1 (type: boolean), cboolean2 (type: boolean) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 - Statistics: Num rows: 4096 Data size: 1031250 Basic stats: COMPLETE Column stats: COMPLETE + expressions: ctinyint (type: tinyint), csmallint (type: smallint), cint (type: int), cbigint (type: bigint), cfloat (type: float), cdouble (type: double), cstring1 (type: string), cstring2 (type: string), ctimestamp1 (type: timestamp), ctimestamp2 (type: timestamp), cboolean1 (type: boolean), cboolean2 (type: boolean), UDFToInteger(csmallint) (type: int) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 + Statistics: Num rows: 4096 Data size: 1043486 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator - key expressions: UDFToInteger(_col1) (type: int) + key expressions: _col12 (type: int) sort order: + - Map-reduce partition columns: UDFToInteger(_col1) (type: int) - Statistics: Num rows: 4096 Data size: 1031250 Basic stats: COMPLETE Column stats: COMPLETE + Map-reduce partition columns: _col12 (type: int) + Statistics: Num rows: 4096 Data size: 1043486 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: tinyint), _col1 (type: smallint), _col2 (type: int), _col3 (type: bigint), _col4 (type: float), _col5 (type: double), _col6 (type: string), _col7 (type: string), _col8 (type: timestamp), _col9 (type: timestamp), _col10 (type: boolean), _col11 (type: boolean) Execution mode: vectorized, llap LLAP IO: all inputs @@ -72,14 +72,14 @@ STAGE PLANS: 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) + expressions: UDFToInteger(key) (type: int) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator - key expressions: UDFToInteger(_col0) (type: int) + key expressions: _col0 (type: int) sort order: + - Map-reduce partition columns: UDFToInteger(_col0) (type: int) - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: no inputs Map 5 @@ -92,14 +92,14 @@ STAGE PLANS: 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) + expressions: (UDFToInteger(key) + 0) (type: int) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator - key expressions: (UDFToInteger(_col0) + 0) (type: int) + key expressions: _col0 (type: int) sort order: + - Map-reduce partition columns: (UDFToInteger(_col0) + 0) (type: int) - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: no inputs Reducer 2 @@ -110,9 +110,9 @@ STAGE PLANS: Inner Join 0 to 1 Inner Join 0 to 2 keys: - 0 UDFToInteger(_col1) (type: int) - 1 UDFToInteger(_col0) (type: int) - 2 (UDFToInteger(_col0) + 0) (type: int) + 0 _col12 (type: int) + 1 _col0 (type: int) + 2 _col0 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 Statistics: Num rows: 791 Data size: 6700 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator @@ -251,14 +251,14 @@ STAGE PLANS: predicate: (csmallint < 100S) (type: boolean) Statistics: Num rows: 4096 Data size: 1031250 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: ctinyint (type: tinyint), csmallint (type: smallint), cint (type: int), cbigint (type: bigint), cfloat (type: float), cdouble (type: double), cstring1 (type: string), cstring2 (type: string), ctimestamp1 (type: timestamp), ctimestamp2 (type: timestamp), cboolean1 (type: boolean), cboolean2 (type: boolean) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 - Statistics: Num rows: 4096 Data size: 1031250 Basic stats: COMPLETE Column stats: COMPLETE + expressions: ctinyint (type: tinyint), csmallint (type: smallint), cint (type: int), cbigint (type: bigint), cfloat (type: float), cdouble (type: double), cstring1 (type: string), cstring2 (type: string), ctimestamp1 (type: timestamp), ctimestamp2 (type: timestamp), cboolean1 (type: boolean), cboolean2 (type: boolean), UDFToInteger(csmallint) (type: int) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 + Statistics: Num rows: 4096 Data size: 1043486 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator - key expressions: UDFToInteger(_col1) (type: int) + key expressions: _col12 (type: int) sort order: + - Map-reduce partition columns: UDFToInteger(_col1) (type: int) - Statistics: Num rows: 4096 Data size: 1031250 Basic stats: COMPLETE Column stats: COMPLETE + Map-reduce partition columns: _col12 (type: int) + Statistics: Num rows: 4096 Data size: 1043486 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: tinyint), _col1 (type: smallint), _col2 (type: int), _col3 (type: bigint), _col4 (type: float), _col5 (type: double), _col6 (type: string), _col7 (type: string), _col8 (type: timestamp), _col9 (type: timestamp), _col10 (type: boolean), _col11 (type: boolean) Execution mode: vectorized, llap LLAP IO: all inputs @@ -272,14 +272,14 @@ STAGE PLANS: 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) + expressions: UDFToInteger(key) (type: int) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator - key expressions: UDFToInteger(_col0) (type: int) + key expressions: _col0 (type: int) sort order: + - Map-reduce partition columns: UDFToInteger(_col0) (type: int) - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: no inputs Map 5 @@ -292,14 +292,14 @@ STAGE PLANS: 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) + expressions: (UDFToInteger(key) + 0) (type: int) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator - key expressions: (UDFToInteger(_col0) + 0) (type: int) + key expressions: _col0 (type: int) sort order: + - Map-reduce partition columns: (UDFToInteger(_col0) + 0) (type: int) - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: no inputs Reducer 2 @@ -310,9 +310,9 @@ STAGE PLANS: Inner Join 0 to 1 Inner Join 0 to 2 keys: - 0 UDFToInteger(_col1) (type: int) - 1 UDFToInteger(_col0) (type: int) - 2 (UDFToInteger(_col0) + 0) (type: int) + 0 _col12 (type: int) + 1 _col0 (type: int) + 2 _col0 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 Statistics: Num rows: 791 Data size: 6700 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator @@ -451,14 +451,14 @@ STAGE PLANS: predicate: (csmallint < 100S) (type: boolean) Statistics: Num rows: 4096 Data size: 1031250 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: ctinyint (type: tinyint), csmallint (type: smallint), cint (type: int), cbigint (type: bigint), cfloat (type: float), cdouble (type: double), cstring1 (type: string), cstring2 (type: string), ctimestamp1 (type: timestamp), ctimestamp2 (type: timestamp), cboolean1 (type: boolean), cboolean2 (type: boolean) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 - Statistics: Num rows: 4096 Data size: 1031250 Basic stats: COMPLETE Column stats: COMPLETE + expressions: ctinyint (type: tinyint), csmallint (type: smallint), cint (type: int), cbigint (type: bigint), cfloat (type: float), cdouble (type: double), cstring1 (type: string), cstring2 (type: string), ctimestamp1 (type: timestamp), ctimestamp2 (type: timestamp), cboolean1 (type: boolean), cboolean2 (type: boolean), UDFToInteger(csmallint) (type: int) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 + Statistics: Num rows: 4096 Data size: 1043486 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator - key expressions: UDFToInteger(_col1) (type: int) + key expressions: _col12 (type: int) sort order: + - Map-reduce partition columns: UDFToInteger(_col1) (type: int) - Statistics: Num rows: 4096 Data size: 1031250 Basic stats: COMPLETE Column stats: COMPLETE + Map-reduce partition columns: _col12 (type: int) + Statistics: Num rows: 4096 Data size: 1043486 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: tinyint), _col1 (type: smallint), _col2 (type: int), _col3 (type: bigint), _col4 (type: float), _col5 (type: double), _col6 (type: string), _col7 (type: string), _col8 (type: timestamp), _col9 (type: timestamp), _col10 (type: boolean), _col11 (type: boolean) Execution mode: vectorized, llap LLAP IO: all inputs @@ -472,14 +472,14 @@ STAGE PLANS: 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) + expressions: UDFToInteger(key) (type: int) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator - key expressions: UDFToInteger(_col0) (type: int) + key expressions: _col0 (type: int) sort order: + - Map-reduce partition columns: UDFToInteger(_col0) (type: int) - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: no inputs Map 5 @@ -492,14 +492,14 @@ STAGE PLANS: 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) + expressions: (UDFToInteger(key) + 0) (type: int) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator - key expressions: (UDFToInteger(_col0) + 0) (type: int) + key expressions: _col0 (type: int) sort order: + - Map-reduce partition columns: (UDFToInteger(_col0) + 0) (type: int) - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: no inputs Reducer 2 @@ -510,9 +510,9 @@ STAGE PLANS: Inner Join 0 to 1 Inner Join 0 to 2 keys: - 0 UDFToInteger(_col1) (type: int) - 1 UDFToInteger(_col0) (type: int) - 2 (UDFToInteger(_col0) + 0) (type: int) + 0 _col12 (type: int) + 1 _col0 (type: int) + 2 _col0 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 Statistics: Num rows: 791 Data size: 6700 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator