diff --git ql/src/test/results/clientpositive/auto_join_filters.q.out ql/src/test/results/clientpositive/auto_join_filters.q.out index a6720d9..110f0f1 100644 --- ql/src/test/results/clientpositive/auto_join_filters.q.out +++ ql/src/test/results/clientpositive/auto_join_filters.q.out @@ -216,6 +216,7 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@myinput1 #### A masked pattern was here #### 3080335 +Warning: Map Join MAPJOIN[36][bigTable=?] in task 'Stage-8:MAPRED' is a cross product PREHOOK: query: SELECT sum(hash(a.key,a.value,b.key,b.value)) FROM myinput1 a LEFT OUTER JOIN myinput1 b RIGHT OUTER JOIN myinput1 c ON a.value = b.value and b.value = c.value AND a.key > 40 AND a.value > 50 AND a.key = a.value AND b.key > 40 AND b.value > 50 AND b.key = b.value AND c.key > 40 AND c.value > 50 AND c.key = c.value PREHOOK: type: QUERY PREHOOK: Input: default@myinput1 @@ -243,6 +244,7 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@myinput1 #### A masked pattern was here #### 3080335 +Warning: Map Join MAPJOIN[36][bigTable=?] in task 'Stage-8:MAPRED' is a cross product PREHOOK: query: SELECT sum(hash(a.key,a.value,b.key,b.value)) FROM myinput1 a LEFT OUTER JOIN myinput1 b RIGHT OUTER JOIN myinput1 c ON a.value = b.value and b.key = c.key AND a.key > 40 AND a.value > 50 AND a.key = a.value AND b.key > 40 AND b.value > 50 AND b.key = b.value AND c.key > 40 AND c.value > 50 AND c.key = c.value PREHOOK: type: QUERY PREHOOK: Input: default@myinput1 @@ -502,6 +504,7 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@myinput1 #### A masked pattern was here #### 3078400 +Warning: Map Join MAPJOIN[41][bigTable=?] in task 'Stage-8:MAPRED' is a cross product PREHOOK: query: SELECT sum(hash(a.key,a.value,b.key,b.value)) FROM myinput1 a LEFT OUTER JOIN myinput1 b RIGHT OUTER JOIN myinput1 c ON a.value = b.value and b.value = c.value AND a.key > 40 AND a.value > 50 AND a.key = a.value AND b.key > 40 AND b.value > 50 AND b.key = b.value AND c.key > 40 AND c.value > 50 AND c.key = c.value PREHOOK: type: QUERY PREHOOK: Input: default@myinput1 @@ -529,6 +532,7 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@myinput1 #### A masked pattern was here #### 3078400 +Warning: Map Join MAPJOIN[41][bigTable=?] in task 'Stage-8:MAPRED' is a cross product PREHOOK: query: SELECT sum(hash(a.key,a.value,b.key,b.value)) FROM myinput1 a LEFT OUTER JOIN myinput1 b RIGHT OUTER JOIN myinput1 c ON a.value = b.value and b.key = c.key AND a.key > 40 AND a.value > 50 AND a.key = a.value AND b.key > 40 AND b.value > 50 AND b.key = b.value AND c.key > 40 AND c.value > 50 AND c.key = c.value PREHOOK: type: QUERY PREHOOK: Input: default@myinput1 diff --git ql/src/test/results/clientpositive/auto_join_nulls.q.out ql/src/test/results/clientpositive/auto_join_nulls.q.out index 4416f3e..338b343 100644 --- ql/src/test/results/clientpositive/auto_join_nulls.q.out +++ ql/src/test/results/clientpositive/auto_join_nulls.q.out @@ -206,6 +206,7 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@myinput1 #### A masked pattern was here #### 3113558 +Warning: Map Join MAPJOIN[28][bigTable=a] in task 'Stage-8:MAPRED' is a cross product PREHOOK: query: SELECT sum(hash(a.key,a.value,b.key,b.value)) FROM myinput1 a LEFT OUTER JOIN myinput1 b RIGHT OUTER JOIN myinput1 c ON a.value = b.value and b.value = c.value PREHOOK: type: QUERY PREHOOK: Input: default@myinput1 diff --git ql/src/test/results/clientpositive/avrocountemptytbl.q.out ql/src/test/results/clientpositive/avrocountemptytbl.q.out index 72e8489..9641a51 100644 --- ql/src/test/results/clientpositive/avrocountemptytbl.q.out +++ ql/src/test/results/clientpositive/avrocountemptytbl.q.out @@ -27,7 +27,7 @@ POSTHOOK: query: insert into emptyavro select count(*) from emptyavro POSTHOOK: type: QUERY POSTHOOK: Input: default@emptyavro POSTHOOK: Output: default@emptyavro -POSTHOOK: Lineage: emptyavro.a EXPRESSION [(emptyavro)emptyavro.null, ] +POSTHOOK: Lineage: emptyavro.a EXPRESSION [] PREHOOK: query: select count(*) from emptyavro PREHOOK: type: QUERY PREHOOK: Input: default@emptyavro diff --git ql/src/test/results/clientpositive/cross_join.q.out ql/src/test/results/clientpositive/cross_join.q.out index 0b80624..81e9ef5 100644 --- ql/src/test/results/clientpositive/cross_join.q.out +++ ql/src/test/results/clientpositive/cross_join.q.out @@ -217,7 +217,7 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 500 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -280,7 +280,7 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 500 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 diff --git ql/src/test/results/clientpositive/dynamic_rdd_cache.q.out ql/src/test/results/clientpositive/dynamic_rdd_cache.q.out index 394af7e..69fe396 100644 --- ql/src/test/results/clientpositive/dynamic_rdd_cache.q.out +++ ql/src/test/results/clientpositive/dynamic_rdd_cache.q.out @@ -1066,23 +1066,19 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - Select Operator - expressions: _col1 (type: int), _col2 (type: int), _col3 (type: int), _col4 (type: double), _col5 (type: double) - outputColumnNames: _col1, _col2, _col3, _col4, _col5 + Filter Operator + predicate: (CASE (_col5) WHEN (0) THEN (0) ELSE ((_col4 / _col5)) END > 1) (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - Filter Operator - predicate: (CASE (_col5) WHEN (0) THEN (0) ELSE ((_col4 / _col5)) END > 1) (type: boolean) + Select Operator + expressions: _col1 (type: int), _col2 (type: int), _col3 (type: int), _col5 (type: double), CASE (_col5) WHEN (0) THEN (null) ELSE ((_col4 / _col5)) END (type: double) + outputColumnNames: _col1, _col2, _col3, _col5, _col6 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - Select Operator - expressions: _col1 (type: int), _col2 (type: int), _col3 (type: int), _col5 (type: double), CASE (_col5) WHEN (0) THEN (null) ELSE ((_col4 / _col5)) END (type: double) - outputColumnNames: _col1, _col2, _col3, _col5, _col6 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - File Output Operator - compressed: true - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + File Output Operator + compressed: true + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-5 Map Reduce @@ -1293,23 +1289,19 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - Select Operator - expressions: _col1 (type: int), _col2 (type: int), _col3 (type: int), _col4 (type: double), _col5 (type: double) - outputColumnNames: _col1, _col2, _col3, _col4, _col5 + Filter Operator + predicate: (CASE (_col5) WHEN (0) THEN (0) ELSE ((_col4 / _col5)) END > 1) (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - Filter Operator - predicate: (CASE (_col5) WHEN (0) THEN (0) ELSE ((_col4 / _col5)) END > 1) (type: boolean) + Select Operator + expressions: _col1 (type: int), _col2 (type: int), _col3 (type: int), _col5 (type: double), CASE (_col5) WHEN (0) THEN (null) ELSE ((_col4 / _col5)) END (type: double) + outputColumnNames: _col1, _col2, _col3, _col5, _col6 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - Select Operator - expressions: _col1 (type: int), _col2 (type: int), _col3 (type: int), _col5 (type: double), CASE (_col5) WHEN (0) THEN (null) ELSE ((_col4 / _col5)) END (type: double) - outputColumnNames: _col1, _col2, _col3, _col5, _col6 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - File Output Operator - compressed: true - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + File Output Operator + compressed: true + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-0 Fetch Operator diff --git ql/src/test/results/clientpositive/join_filters.q.out ql/src/test/results/clientpositive/join_filters.q.out index 4f112bd..47dc77b 100644 --- ql/src/test/results/clientpositive/join_filters.q.out +++ ql/src/test/results/clientpositive/join_filters.q.out @@ -308,6 +308,7 @@ NULL NULL 12 35 NULL NULL NULL NULL 48 NULL NULL NULL NULL NULL NULL 40 NULL NULL BYad/CYbc/RASCgl63S7Ww== +Warning: Shuffle Join JOIN[5][tables = [a, b]] in Stage 'Stage-1:MAPRED' is a cross product PREHOOK: query: SELECT * FROM myinput1 a LEFT OUTER JOIN myinput1 b RIGHT OUTER JOIN myinput1 c ON a.value = b.value and b.value = c.value AND a.key > 40 AND a.value > 50 AND a.key = a.value AND b.key > 40 AND b.value > 50 AND b.key = b.value AND c.key > 40 AND c.value > 50 AND c.key = c.value PREHOOK: type: QUERY PREHOOK: Input: default@myinput1 @@ -347,6 +348,7 @@ NULL NULL 12 35 NULL NULL NULL NULL 48 NULL NULL NULL NULL NULL NULL 40 NULL NULL BYad/CYbc/RASCgl63S7Ww== +Warning: Shuffle Join JOIN[5][tables = [a, b]] in Stage 'Stage-1:MAPRED' is a cross product PREHOOK: query: SELECT * FROM myinput1 a LEFT OUTER JOIN myinput1 b RIGHT OUTER JOIN myinput1 c ON a.value = b.value and b.key = c.key AND a.key > 40 AND a.value > 50 AND a.key = a.value AND b.key > 40 AND b.value > 50 AND b.key = b.value AND c.key > 40 AND c.value > 50 AND c.key = c.value PREHOOK: type: QUERY PREHOOK: Input: default@myinput1 @@ -998,6 +1000,7 @@ POSTHOOK: Input: default@myinput1 #### A masked pattern was here #### 100 100 100 100 100 100 WPjT9iK+FjpywFhoiQ0jvw== +Warning: Shuffle Join JOIN[8][tables = [a, b]] in Stage 'Stage-1:MAPRED' is a cross product PREHOOK: query: SELECT * FROM myinput1 a LEFT OUTER JOIN myinput1 b RIGHT OUTER JOIN myinput1 c ON a.value = b.value and b.value = c.value AND a.key > 40 AND a.value > 50 AND a.key = a.value AND b.key > 40 AND b.value > 50 AND b.key = b.value AND c.key > 40 AND c.value > 50 AND c.key = c.value PREHOOK: type: QUERY PREHOOK: Input: default@myinput1 @@ -1028,6 +1031,7 @@ POSTHOOK: Input: default@myinput1 #### A masked pattern was here #### 100 100 100 100 100 100 WPjT9iK+FjpywFhoiQ0jvw== +Warning: Shuffle Join JOIN[8][tables = [a, b]] in Stage 'Stage-1:MAPRED' is a cross product PREHOOK: query: SELECT * FROM myinput1 a LEFT OUTER JOIN myinput1 b RIGHT OUTER JOIN myinput1 c ON a.value = b.value and b.key = c.key AND a.key > 40 AND a.value > 50 AND a.key = a.value AND b.key > 40 AND b.value > 50 AND b.key = b.value AND c.key > 40 AND c.value > 50 AND c.key = c.value PREHOOK: type: QUERY PREHOOK: Input: default@myinput1 diff --git ql/src/test/results/clientpositive/join_merge_multi_expressions.q.out ql/src/test/results/clientpositive/join_merge_multi_expressions.q.out index a8bd4df..b73643e 100644 --- ql/src/test/results/clientpositive/join_merge_multi_expressions.q.out +++ ql/src/test/results/clientpositive/join_merge_multi_expressions.q.out @@ -21,42 +21,54 @@ STAGE PLANS: Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: key (type: string), hr (type: string) - sort order: ++ - Map-reduce partition columns: key (type: string), hr (type: string) + Select Operator + expressions: key (type: string), hr (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) + Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE TableScan - alias: b + alias: a Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: key (type: string), hr (type: string) - sort order: ++ - Map-reduce partition columns: key (type: string), hr (type: string) + Select Operator + expressions: key (type: string), hr (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) + Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE TableScan - alias: c + alias: a Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: key (type: string), hr (type: string) - sort order: ++ - Map-reduce partition columns: key (type: string), hr (type: string) + Select Operator + expressions: key (type: string), hr (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) + Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 Inner Join 0 to 2 keys: - 0 key (type: string), hr (type: string) - 1 key (type: string), hr (type: string) - 2 key (type: string), hr (type: string) + 0 _col0 (type: string), _col1 (type: string) + 1 _col0 (type: string), _col1 (type: string) + 2 _col0 (type: string), _col1 (type: string) Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() diff --git ql/src/test/results/clientpositive/join_nulls.q.out ql/src/test/results/clientpositive/join_nulls.q.out index b536985..e262f58 100644 --- ql/src/test/results/clientpositive/join_nulls.q.out +++ ql/src/test/results/clientpositive/join_nulls.q.out @@ -270,6 +270,7 @@ POSTHOOK: Input: default@myinput1 100 100 100 100 100 100 NULL 35 NULL 35 NULL 35 NULL NULL 48 NULL NULL NULL +Warning: Shuffle Join JOIN[5][tables = [a, b]] in Stage 'Stage-1:MAPRED' is a cross product PREHOOK: query: SELECT * FROM myinput1 a LEFT OUTER JOIN myinput1 b RIGHT OUTER JOIN myinput1 c ON a.value = b.value and b.value = c.value PREHOOK: type: QUERY PREHOOK: Input: default@myinput1 diff --git ql/src/test/results/clientpositive/orc_merge10.q.out ql/src/test/results/clientpositive/orc_merge10.q.out index a415776..d16ca18 100644 --- ql/src/test/results/clientpositive/orc_merge10.q.out +++ ql/src/test/results/clientpositive/orc_merge10.q.out @@ -517,11 +517,11 @@ PREHOOK: Input: default@orcfile_merge1@ds=1/part=0 #### A masked pattern was here #### -- BEGIN ORC FILE DUMP -- #### A masked pattern was here #### -File Version: 0.12 with HIVE_4243 +File Version: 0.12 with HIVE_8732 Rows: 242 Compression: SNAPPY Compression size: 4096 -Type: struct +Type: struct<_col0:int,_col1:string> Stripe Statistics: Stripe 1: @@ -565,7 +565,7 @@ Stripes: Row group indices for column 1: Entry 0: count: 90 hasNull: false min: 0 max: 495 sum: 22736 positions: 0,0,0 -File length: 2137 bytes +File length: 2139 bytes Padding length: 0 bytes Padding ratio: 0% ________________________________________________________________________________________________________________________ @@ -579,11 +579,11 @@ PREHOOK: Input: default@orcfile_merge1c@ds=1/part=0 #### A masked pattern was here #### -- BEGIN ORC FILE DUMP -- #### A masked pattern was here #### -File Version: 0.12 with HIVE_4243 +File Version: 0.12 with HIVE_8732 Rows: 242 Compression: SNAPPY Compression size: 4096 -Type: struct +Type: struct<_col0:int,_col1:string> Stripe Statistics: Stripe 1: @@ -627,7 +627,7 @@ Stripes: Row group indices for column 1: Entry 0: count: 90 hasNull: false min: 0 max: 495 sum: 22736 positions: 0,0,0 -File length: 2137 bytes +File length: 2139 bytes Padding length: 0 bytes Padding ratio: 0% ________________________________________________________________________________________________________________________ diff --git ql/src/test/results/clientpositive/parquet_mixed_partition_formats.q.out ql/src/test/results/clientpositive/parquet_mixed_partition_formats.q.out index a412350..18c7c05 100644 --- ql/src/test/results/clientpositive/parquet_mixed_partition_formats.q.out +++ ql/src/test/results/clientpositive/parquet_mixed_partition_formats.q.out @@ -124,6 +124,8 @@ Partition Value: [20140330] Database: default Table: parquet_mixed_partition_formats #### A masked pattern was here #### +Protect Mode: None +#### A masked pattern was here #### Partition Parameters: COLUMN_STATS_ACCURATE true numFiles 1 @@ -196,6 +198,7 @@ dateint int # Detailed Table Information Database: default #### A masked pattern was here #### +Protect Mode: None Retention: 0 #### A masked pattern was here #### Table Type: MANAGED_TABLE @@ -248,6 +251,8 @@ Partition Value: [20140330] Database: default Table: parquet_mixed_partition_formats #### A masked pattern was here #### +Protect Mode: None +#### A masked pattern was here #### Partition Parameters: COLUMN_STATS_ACCURATE true numFiles 1 diff --git ql/src/test/results/clientpositive/spark/vector_outer_join1.q.out ql/src/test/results/clientpositive/spark/vector_outer_join1.q.out index cfc4753..c96aa56 100644 --- ql/src/test/results/clientpositive/spark/vector_outer_join1.q.out +++ ql/src/test/results/clientpositive/spark/vector_outer_join1.q.out @@ -181,16 +181,12 @@ STAGE PLANS: Map 2 Map Operator Tree: TableScan - alias: c + alias: cd Statistics: Num rows: 15 Data size: 3915 Basic stats: COMPLETE Column stats: NONE - 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: 15 Data size: 3915 Basic stats: COMPLETE Column stats: NONE - Spark HashTable Sink Operator - keys: - 0 _col2 (type: int) - 1 _col2 (type: int) + Spark HashTable Sink Operator + keys: + 0 cint (type: int) + 1 cint (type: int) Local Work: Map Reduce Local Work Execution mode: vectorized @@ -204,19 +200,19 @@ STAGE PLANS: TableScan alias: c Statistics: Num rows: 15 Data size: 3915 Basic stats: COMPLETE Column stats: NONE - 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: 15 Data size: 3915 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Left Outer Join0 to 1 - keys: - 0 _col2 (type: int) - 1 _col2 (type: int) + Map Join Operator + condition map: + Left Outer Join0 to 1 + keys: + 0 cint (type: int) + 1 cint (type: int) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26 + input vertices: + 1 Map 2 + Statistics: Num rows: 16 Data size: 4306 Basic stats: COMPLETE Column stats: NONE + Select Operator + 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), _col15 (type: tinyint), _col16 (type: smallint), _col17 (type: int), _col18 (type: bigint), _col19 (type: float), _col20 (type: double), _col21 (type: string), _col22 (type: string), _col23 (type: timestamp), _col24 (type: timestamp), _col25 (type: boolean), _col26 (type: boolean) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23 - input vertices: - 1 Map 2 Statistics: Num rows: 16 Data size: 4306 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -297,16 +293,12 @@ STAGE PLANS: Map 2 Map Operator Tree: TableScan - alias: c + alias: hd Statistics: Num rows: 15 Data size: 3915 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: ctinyint (type: tinyint) - outputColumnNames: _col0 - Statistics: Num rows: 15 Data size: 3915 Basic stats: COMPLETE Column stats: NONE - Spark HashTable Sink Operator - keys: - 0 _col0 (type: tinyint) - 1 _col0 (type: tinyint) + Spark HashTable Sink Operator + keys: + 0 ctinyint (type: tinyint) + 1 ctinyint (type: tinyint) Local Work: Map Reduce Local Work Execution mode: vectorized @@ -320,27 +312,23 @@ STAGE PLANS: TableScan alias: c Statistics: Num rows: 15 Data size: 3915 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: ctinyint (type: tinyint) + Map Join Operator + condition map: + Left Outer Join0 to 1 + keys: + 0 ctinyint (type: tinyint) + 1 ctinyint (type: tinyint) outputColumnNames: _col0 - Statistics: Num rows: 15 Data size: 3915 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Left Outer Join0 to 1 - keys: - 0 _col0 (type: tinyint) - 1 _col0 (type: tinyint) - outputColumnNames: _col0 - input vertices: - 1 Map 2 + input vertices: + 1 Map 2 + Statistics: Num rows: 16 Data size: 4306 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false Statistics: Num rows: 16 Data size: 4306 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 16 Data size: 4306 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Local Work: Map Reduce Local Work Execution mode: vectorized diff --git ql/src/test/results/clientpositive/spark/vector_outer_join2.q.out ql/src/test/results/clientpositive/spark/vector_outer_join2.q.out index 38051fd..0015708 100644 --- ql/src/test/results/clientpositive/spark/vector_outer_join2.q.out +++ ql/src/test/results/clientpositive/spark/vector_outer_join2.q.out @@ -262,15 +262,19 @@ STAGE PLANS: input vertices: 1 Map 4 Statistics: Num rows: 24 Data size: 6117 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(), sum(_col1) - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: + Select Operator + expressions: _col1 (type: bigint) + outputColumnNames: _col0 + Statistics: Num rows: 24 Data size: 6117 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count(), sum(_col0) + mode: hash + outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint), _col1 (type: bigint) + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint), _col1 (type: bigint) Local Work: Map Reduce Local Work Execution mode: vectorized diff --git ql/src/test/results/clientpositive/spark/vector_outer_join4.q.out ql/src/test/results/clientpositive/spark/vector_outer_join4.q.out index 182dbb0..8d1f680 100644 --- ql/src/test/results/clientpositive/spark/vector_outer_join4.q.out +++ ql/src/test/results/clientpositive/spark/vector_outer_join4.q.out @@ -211,16 +211,12 @@ STAGE PLANS: Map 2 Map Operator Tree: TableScan - alias: c + alias: cd Statistics: Num rows: 30 Data size: 4298 Basic stats: COMPLETE Column stats: NONE - 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: 30 Data size: 4298 Basic stats: COMPLETE Column stats: NONE - Spark HashTable Sink Operator - keys: - 0 _col2 (type: int) - 1 _col2 (type: int) + Spark HashTable Sink Operator + keys: + 0 cint (type: int) + 1 cint (type: int) Local Work: Map Reduce Local Work Execution mode: vectorized @@ -234,19 +230,19 @@ STAGE PLANS: TableScan alias: c Statistics: Num rows: 30 Data size: 4298 Basic stats: COMPLETE Column stats: NONE - 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: 30 Data size: 4298 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Left Outer Join0 to 1 - keys: - 0 _col2 (type: int) - 1 _col2 (type: int) + Map Join Operator + condition map: + Left Outer Join0 to 1 + keys: + 0 cint (type: int) + 1 cint (type: int) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26 + input vertices: + 1 Map 2 + Statistics: Num rows: 33 Data size: 4727 Basic stats: COMPLETE Column stats: NONE + Select Operator + 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), _col15 (type: tinyint), _col16 (type: smallint), _col17 (type: int), _col18 (type: bigint), _col19 (type: float), _col20 (type: double), _col21 (type: string), _col22 (type: string), _col23 (type: timestamp), _col24 (type: timestamp), _col25 (type: boolean), _col26 (type: boolean) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23 - input vertices: - 1 Map 2 Statistics: Num rows: 33 Data size: 4727 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -362,16 +358,12 @@ STAGE PLANS: Map 2 Map Operator Tree: TableScan - alias: c + alias: hd Statistics: Num rows: 30 Data size: 4298 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: ctinyint (type: tinyint) - outputColumnNames: _col0 - Statistics: Num rows: 30 Data size: 4298 Basic stats: COMPLETE Column stats: NONE - Spark HashTable Sink Operator - keys: - 0 _col0 (type: tinyint) - 1 _col0 (type: tinyint) + Spark HashTable Sink Operator + keys: + 0 ctinyint (type: tinyint) + 1 ctinyint (type: tinyint) Local Work: Map Reduce Local Work Execution mode: vectorized @@ -385,27 +377,23 @@ STAGE PLANS: TableScan alias: c Statistics: Num rows: 30 Data size: 4298 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: ctinyint (type: tinyint) + Map Join Operator + condition map: + Left Outer Join0 to 1 + keys: + 0 ctinyint (type: tinyint) + 1 ctinyint (type: tinyint) outputColumnNames: _col0 - Statistics: Num rows: 30 Data size: 4298 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Left Outer Join0 to 1 - keys: - 0 _col0 (type: tinyint) - 1 _col0 (type: tinyint) - outputColumnNames: _col0 - input vertices: - 1 Map 2 + input vertices: + 1 Map 2 + Statistics: Num rows: 33 Data size: 4727 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false Statistics: Num rows: 33 Data size: 4727 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 33 Data size: 4727 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Local Work: Map Reduce Local Work Execution mode: vectorized diff --git ql/src/test/results/clientpositive/tez/auto_join_filters.q.out ql/src/test/results/clientpositive/tez/auto_join_filters.q.out index 8fde41d..f599335 100644 --- ql/src/test/results/clientpositive/tez/auto_join_filters.q.out +++ ql/src/test/results/clientpositive/tez/auto_join_filters.q.out @@ -216,6 +216,7 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@myinput1 #### A masked pattern was here #### 3080335 +Warning: Map Join MAPJOIN[26][bigTable=?] in task 'Map 1' is a cross product PREHOOK: query: SELECT sum(hash(a.key,a.value,b.key,b.value)) FROM myinput1 a LEFT OUTER JOIN myinput1 b RIGHT OUTER JOIN myinput1 c ON a.value = b.value and b.value = c.value AND a.key > 40 AND a.value > 50 AND a.key = a.value AND b.key > 40 AND b.value > 50 AND b.key = b.value AND c.key > 40 AND c.value > 50 AND c.key = c.value PREHOOK: type: QUERY PREHOOK: Input: default@myinput1 @@ -243,6 +244,7 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@myinput1 #### A masked pattern was here #### 3080335 +Warning: Map Join MAPJOIN[26][bigTable=?] in task 'Map 1' is a cross product PREHOOK: query: SELECT sum(hash(a.key,a.value,b.key,b.value)) FROM myinput1 a LEFT OUTER JOIN myinput1 b RIGHT OUTER JOIN myinput1 c ON a.value = b.value and b.key = c.key AND a.key > 40 AND a.value > 50 AND a.key = a.value AND b.key > 40 AND b.value > 50 AND b.key = b.value AND c.key > 40 AND c.value > 50 AND c.key = c.value PREHOOK: type: QUERY PREHOOK: Input: default@myinput1 @@ -502,6 +504,7 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@myinput1 #### A masked pattern was here #### 3078400 +Warning: Map Join MAPJOIN[30][bigTable=?] in task 'Map 1' is a cross product PREHOOK: query: SELECT sum(hash(a.key,a.value,b.key,b.value)) FROM myinput1 a LEFT OUTER JOIN myinput1 b RIGHT OUTER JOIN myinput1 c ON a.value = b.value and b.value = c.value AND a.key > 40 AND a.value > 50 AND a.key = a.value AND b.key > 40 AND b.value > 50 AND b.key = b.value AND c.key > 40 AND c.value > 50 AND c.key = c.value PREHOOK: type: QUERY PREHOOK: Input: default@myinput1 @@ -529,6 +532,7 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@myinput1 #### A masked pattern was here #### 3078400 +Warning: Map Join MAPJOIN[30][bigTable=?] in task 'Map 1' is a cross product PREHOOK: query: SELECT sum(hash(a.key,a.value,b.key,b.value)) FROM myinput1 a LEFT OUTER JOIN myinput1 b RIGHT OUTER JOIN myinput1 c ON a.value = b.value and b.key = c.key AND a.key > 40 AND a.value > 50 AND a.key = a.value AND b.key > 40 AND b.value > 50 AND b.key = b.value AND c.key > 40 AND c.value > 50 AND c.key = c.value PREHOOK: type: QUERY PREHOOK: Input: default@myinput1 diff --git ql/src/test/results/clientpositive/tez/cross_join.q.out ql/src/test/results/clientpositive/tez/cross_join.q.out index f772887..d9023d9 100644 --- ql/src/test/results/clientpositive/tez/cross_join.q.out +++ ql/src/test/results/clientpositive/tez/cross_join.q.out @@ -251,10 +251,10 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 500 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 500 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE Stage: Stage-0 Fetch Operator @@ -310,10 +310,10 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 500 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 500 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE Stage: Stage-0 Fetch Operator diff --git ql/src/test/results/clientpositive/tez/orc_merge10.q.out ql/src/test/results/clientpositive/tez/orc_merge10.q.out index d41671a..bb9d9da 100644 --- ql/src/test/results/clientpositive/tez/orc_merge10.q.out +++ ql/src/test/results/clientpositive/tez/orc_merge10.q.out @@ -552,11 +552,11 @@ PREHOOK: Input: default@orcfile_merge1@ds=1/part=0 #### A masked pattern was here #### -- BEGIN ORC FILE DUMP -- #### A masked pattern was here #### -File Version: 0.12 with HIVE_4243 +File Version: 0.12 with HIVE_8732 Rows: 242 Compression: SNAPPY Compression size: 4096 -Type: struct +Type: struct<_col0:int,_col1:string> Stripe Statistics: Stripe 1: @@ -615,7 +615,7 @@ Stripes: Row group indices for column 1: Entry 0: count: 74 hasNull: false min: 2 max: 493 sum: 19663 positions: 0,0,0 -File length: 2393 bytes +File length: 2394 bytes Padding length: 0 bytes Padding ratio: 0% ________________________________________________________________________________________________________________________ @@ -629,11 +629,11 @@ PREHOOK: Input: default@orcfile_merge1c@ds=1/part=0 #### A masked pattern was here #### -- BEGIN ORC FILE DUMP -- #### A masked pattern was here #### -File Version: 0.12 with HIVE_4243 +File Version: 0.12 with HIVE_8732 Rows: 242 Compression: SNAPPY Compression size: 4096 -Type: struct +Type: struct<_col0:int,_col1:string> Stripe Statistics: Stripe 1: @@ -692,7 +692,7 @@ Stripes: Row group indices for column 1: Entry 0: count: 74 hasNull: false min: 2 max: 493 sum: 19663 positions: 0,0,0 -File length: 2393 bytes +File length: 2394 bytes Padding length: 0 bytes Padding ratio: 0% ________________________________________________________________________________________________________________________ diff --git ql/src/test/results/clientpositive/tez/union_fast_stats.q.out ql/src/test/results/clientpositive/tez/union_fast_stats.q.out index d0d82a0..ed392fc 100644 --- ql/src/test/results/clientpositive/tez/union_fast_stats.q.out +++ ql/src/test/results/clientpositive/tez/union_fast_stats.q.out @@ -112,6 +112,7 @@ cboolean2 boolean # Detailed Table Information Database: default #### A masked pattern was here #### +Protect Mode: None Retention: 0 #### A masked pattern was here #### Table Type: MANAGED_TABLE @@ -165,6 +166,7 @@ cboolean2 boolean # Detailed Table Information Database: default #### A masked pattern was here #### +Protect Mode: None Retention: 0 #### A masked pattern was here #### Table Type: MANAGED_TABLE @@ -230,6 +232,7 @@ cboolean2 boolean # Detailed Table Information Database: default #### A masked pattern was here #### +Protect Mode: None Retention: 0 #### A masked pattern was here #### Table Type: MANAGED_TABLE @@ -385,6 +388,7 @@ cboolean2 boolean # Detailed Table Information Database: default #### A masked pattern was here #### +Protect Mode: None Retention: 0 #### A masked pattern was here #### Table Type: MANAGED_TABLE @@ -438,6 +442,7 @@ cboolean2 boolean # Detailed Table Information Database: default #### A masked pattern was here #### +Protect Mode: None Retention: 0 #### A masked pattern was here #### Table Type: MANAGED_TABLE @@ -503,6 +508,7 @@ cboolean2 boolean # Detailed Table Information Database: default #### A masked pattern was here #### +Protect Mode: None Retention: 0 #### A masked pattern was here #### Table Type: MANAGED_TABLE diff --git ql/src/test/results/clientpositive/tez/union_view.q.out ql/src/test/results/clientpositive/tez/union_view.q.out index ae6d7c8..73644bd 100644 --- ql/src/test/results/clientpositive/tez/union_view.q.out +++ ql/src/test/results/clientpositive/tez/union_view.q.out @@ -270,16 +270,21 @@ STAGE PLANS: TableScan alias: src_union_1 filterExpr: ((key = 86) and (ds = '1')) (type: boolean) + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (key = 86) (type: boolean) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: string) outputColumnNames: _col1 + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: 86 (type: int), _col1 (type: string), '1' (type: string) outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 252 Data size: 2656 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false + Statistics: Num rows: 252 Data size: 2656 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -289,16 +294,21 @@ STAGE PLANS: TableScan alias: src_union_2 filterExpr: ((key = 86) and (ds = '1')) (type: boolean) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator predicate: ((key = 86) and (ds = '1')) (type: boolean) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: value (type: string) outputColumnNames: _col1 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: 86 (type: int), _col1 (type: string), '1' (type: string) outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 252 Data size: 2656 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false + Statistics: Num rows: 252 Data size: 2656 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -308,16 +318,21 @@ STAGE PLANS: TableScan alias: src_union_3 filterExpr: ((key = 86) and (ds = '1')) (type: boolean) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator predicate: ((key = 86) and (ds = '1')) (type: boolean) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: value (type: string) outputColumnNames: _col1 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: 86 (type: int), _col1 (type: string), '1' (type: string) outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 252 Data size: 2656 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false + Statistics: Num rows: 252 Data size: 2656 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -349,16 +364,21 @@ STAGE PLANS: TableScan alias: src_union_1 filterExpr: ((key = 86) and (ds = '2')) (type: boolean) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator predicate: ((key = 86) and (ds = '2')) (type: boolean) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: value (type: string) outputColumnNames: _col1 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: 86 (type: int), _col1 (type: string), '2' (type: string) outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 502 Data size: 5312 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false + Statistics: Num rows: 502 Data size: 5312 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -368,16 +388,21 @@ STAGE PLANS: TableScan alias: src_union_2 filterExpr: ((key = 86) and (ds = '2')) (type: boolean) + Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (key = 86) (type: boolean) + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: string) outputColumnNames: _col1 + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: 86 (type: int), _col1 (type: string), '2' (type: string) outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 502 Data size: 5312 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false + Statistics: Num rows: 502 Data size: 5312 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -387,16 +412,21 @@ STAGE PLANS: TableScan alias: src_union_3 filterExpr: ((key = 86) and (ds = '2')) (type: boolean) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator predicate: ((key = 86) and (ds = '2')) (type: boolean) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: value (type: string) outputColumnNames: _col1 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: 86 (type: int), _col1 (type: string), '2' (type: string) outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 502 Data size: 5312 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false + Statistics: Num rows: 502 Data size: 5312 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -428,16 +458,21 @@ STAGE PLANS: TableScan alias: src_union_1 filterExpr: ((key = 86) and (ds = '3')) (type: boolean) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator predicate: ((key = 86) and (ds = '3')) (type: boolean) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: value (type: string) outputColumnNames: _col1 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: 86 (type: int), _col1 (type: string), '3' (type: string) outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 502 Data size: 5312 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false + Statistics: Num rows: 502 Data size: 5312 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -447,16 +482,21 @@ STAGE PLANS: TableScan alias: src_union_2 filterExpr: ((key = 86) and (ds = '3')) (type: boolean) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator predicate: ((key = 86) and (ds = '3')) (type: boolean) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: value (type: string) outputColumnNames: _col1 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: 86 (type: int), _col1 (type: string), '3' (type: string) outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 502 Data size: 5312 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false + Statistics: Num rows: 502 Data size: 5312 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -466,16 +506,21 @@ STAGE PLANS: TableScan alias: src_union_3 filterExpr: ((key = 86) and (ds = '3')) (type: boolean) + Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (key = 86) (type: boolean) + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: string) outputColumnNames: _col1 + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: 86 (type: int), _col1 (type: string), '3' (type: string) outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 502 Data size: 5312 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false + Statistics: Num rows: 502 Data size: 5312 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -508,51 +553,66 @@ STAGE PLANS: TableScan alias: src_union_1 filterExpr: ((key = 86) and ds is not null) (type: boolean) + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (key = 86) (type: boolean) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: string), ds (type: string) outputColumnNames: _col1, _col2 + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col1 (type: string), _col2 (type: string) outputColumnNames: _col1, _col2 + Statistics: Num rows: 1250 Data size: 13280 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col2 (type: string) sort order: + + Statistics: Num rows: 1250 Data size: 13280 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Map 4 Map Operator Tree: TableScan alias: src_union_2 filterExpr: ((key = 86) and ds is not null) (type: boolean) + Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (key = 86) (type: boolean) + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: string), ds (type: string) outputColumnNames: _col1, _col2 + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col1 (type: string), _col2 (type: string) outputColumnNames: _col1, _col2 + Statistics: Num rows: 1250 Data size: 13280 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col2 (type: string) sort order: + + Statistics: Num rows: 1250 Data size: 13280 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Map 5 Map Operator Tree: TableScan alias: src_union_3 filterExpr: ((key = 86) and ds is not null) (type: boolean) + Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (key = 86) (type: boolean) + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: string), ds (type: string) outputColumnNames: _col1, _col2 + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col1 (type: string), _col2 (type: string) outputColumnNames: _col1, _col2 + Statistics: Num rows: 1250 Data size: 13280 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col2 (type: string) sort order: + + Statistics: Num rows: 1250 Data size: 13280 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Reducer 3 Reduce Operator Tree: @@ -605,46 +665,63 @@ STAGE PLANS: TableScan alias: src_union_1 filterExpr: (ds = '1') (type: boolean) + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator + Statistics: Num rows: 502 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(1) mode: hash outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint) Map 4 Map Operator Tree: TableScan alias: src_union_2 filterExpr: (ds = '1') (type: boolean) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator predicate: (ds = '1') (type: boolean) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator + Statistics: Num rows: 502 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(1) mode: hash outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint) Map 5 Map Operator Tree: TableScan alias: src_union_3 filterExpr: (ds = '1') (type: boolean) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator predicate: (ds = '1') (type: boolean) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator + Statistics: Num rows: 502 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(1) mode: hash outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint) Reducer 3 Reduce Operator Tree: @@ -688,46 +765,63 @@ STAGE PLANS: TableScan alias: src_union_1 filterExpr: (ds = '2') (type: boolean) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator predicate: (ds = '2') (type: boolean) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator + Statistics: Num rows: 1002 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(1) mode: hash outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint) Map 4 Map Operator Tree: TableScan alias: src_union_2 filterExpr: (ds = '2') (type: boolean) + Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Select Operator + Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Select Operator + Statistics: Num rows: 1002 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(1) mode: hash outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint) Map 5 Map Operator Tree: TableScan alias: src_union_3 filterExpr: (ds = '2') (type: boolean) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator predicate: (ds = '2') (type: boolean) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator + Statistics: Num rows: 1002 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(1) mode: hash outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint) Reducer 3 Reduce Operator Tree: @@ -771,46 +865,63 @@ STAGE PLANS: TableScan alias: src_union_1 filterExpr: (ds = '3') (type: boolean) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator predicate: (ds = '3') (type: boolean) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator + Statistics: Num rows: 1002 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(1) mode: hash outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint) Map 4 Map Operator Tree: TableScan alias: src_union_2 filterExpr: (ds = '3') (type: boolean) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator predicate: (ds = '3') (type: boolean) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator + Statistics: Num rows: 1002 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(1) mode: hash outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint) Map 5 Map Operator Tree: TableScan alias: src_union_3 filterExpr: (ds = '3') (type: boolean) + Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Select Operator + Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Select Operator + Statistics: Num rows: 1002 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(1) mode: hash outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint) Reducer 3 Reduce Operator Tree: @@ -856,16 +967,21 @@ STAGE PLANS: TableScan alias: src_union_1 filterExpr: ((key = 86) and (ds = '4')) (type: boolean) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator predicate: ((key = 86) and (ds = '4')) (type: boolean) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: value (type: string) outputColumnNames: _col1 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: 86 (type: int), _col1 (type: string), '4' (type: string) outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 252 Data size: 2656 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false + Statistics: Num rows: 252 Data size: 2656 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -875,16 +991,21 @@ STAGE PLANS: TableScan alias: src_union_2 filterExpr: ((key = 86) and (ds = '4')) (type: boolean) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator predicate: ((key = 86) and (ds = '4')) (type: boolean) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: value (type: string) outputColumnNames: _col1 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: 86 (type: int), _col1 (type: string), '4' (type: string) outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 252 Data size: 2656 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false + Statistics: Num rows: 252 Data size: 2656 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -894,16 +1015,21 @@ STAGE PLANS: TableScan alias: src_union_3 filterExpr: ((key = 86) and (ds = '4')) (type: boolean) + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (key = 86) (type: boolean) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: string) outputColumnNames: _col1 + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: 86 (type: int), _col1 (type: string), '4' (type: string) outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 252 Data size: 2656 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false + Statistics: Num rows: 252 Data size: 2656 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -937,46 +1063,63 @@ STAGE PLANS: TableScan alias: src_union_1 filterExpr: (ds = '4') (type: boolean) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator predicate: (ds = '4') (type: boolean) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator + Statistics: Num rows: 502 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(1) mode: hash outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint) Map 4 Map Operator Tree: TableScan alias: src_union_2 filterExpr: (ds = '4') (type: boolean) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator predicate: (ds = '4') (type: boolean) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator + Statistics: Num rows: 502 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(1) mode: hash outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint) Map 5 Map Operator Tree: TableScan alias: src_union_3 filterExpr: (ds = '4') (type: boolean) + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator + Statistics: Num rows: 502 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(1) mode: hash outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint) Reducer 3 Reduce Operator Tree: diff --git ql/src/test/results/clientpositive/tez/vector_join_filters.q.out ql/src/test/results/clientpositive/tez/vector_join_filters.q.out index 8cc9311..92b14eb 100644 --- ql/src/test/results/clientpositive/tez/vector_join_filters.q.out +++ ql/src/test/results/clientpositive/tez/vector_join_filters.q.out @@ -184,6 +184,7 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@myinput1 #### A masked pattern was here #### 3080335 +Warning: Map Join MAPJOIN[26][bigTable=?] in task 'Map 1' is a cross product PREHOOK: query: SELECT sum(hash(a.key,a.value,b.key,b.value)) FROM myinput1 a LEFT OUTER JOIN myinput1 b RIGHT OUTER JOIN myinput1 c ON a.value = b.value and b.value = c.value AND a.key > 40 AND a.value > 50 AND a.key = a.value AND b.key > 40 AND b.value > 50 AND b.key = b.value AND c.key > 40 AND c.value > 50 AND c.key = c.value PREHOOK: type: QUERY PREHOOK: Input: default@myinput1 @@ -211,6 +212,7 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@myinput1 #### A masked pattern was here #### 3080335 +Warning: Map Join MAPJOIN[26][bigTable=?] in task 'Map 1' is a cross product PREHOOK: query: SELECT sum(hash(a.key,a.value,b.key,b.value)) FROM myinput1 a LEFT OUTER JOIN myinput1 b RIGHT OUTER JOIN myinput1 c ON a.value = b.value and b.key = c.key AND a.key > 40 AND a.value > 50 AND a.key = a.value AND b.key > 40 AND b.value > 50 AND b.key = b.value AND c.key > 40 AND c.value > 50 AND c.key = c.value PREHOOK: type: QUERY PREHOOK: Input: default@myinput1 diff --git ql/src/test/results/clientpositive/tez/vector_join_nulls.q.out ql/src/test/results/clientpositive/tez/vector_join_nulls.q.out index 2243072..938717b 100644 --- ql/src/test/results/clientpositive/tez/vector_join_nulls.q.out +++ ql/src/test/results/clientpositive/tez/vector_join_nulls.q.out @@ -184,6 +184,7 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@myinput1 #### A masked pattern was here #### 3113558 +Warning: Map Join MAPJOIN[19][bigTable=a] in task 'Map 1' is a cross product PREHOOK: query: SELECT sum(hash(a.key,a.value,b.key,b.value)) FROM myinput1 a LEFT OUTER JOIN myinput1 b RIGHT OUTER JOIN myinput1 c ON a.value = b.value and b.value = c.value PREHOOK: type: QUERY PREHOOK: Input: default@myinput1 diff --git ql/src/test/results/clientpositive/tez/vector_join_part_col_char.q.out ql/src/test/results/clientpositive/tez/vector_join_part_col_char.q.out index f3d5931..f861103 100644 --- ql/src/test/results/clientpositive/tez/vector_join_part_col_char.q.out +++ ql/src/test/results/clientpositive/tez/vector_join_part_col_char.q.out @@ -87,111 +87,137 @@ PREHOOK: Input: default@char_tbl1 POSTHOOK: query: show partitions char_tbl1 POSTHOOK: type: SHOWPARTITIONS POSTHOOK: Input: default@char_tbl1 -gpa=2.5 -gpa=3.5 +gpa=2.5 +gpa=3.5 PREHOOK: query: show partitions char_tbl2 PREHOOK: type: SHOWPARTITIONS PREHOOK: Input: default@char_tbl2 POSTHOOK: query: show partitions char_tbl2 POSTHOOK: type: SHOWPARTITIONS POSTHOOK: Input: default@char_tbl2 -gpa=3 -gpa=3.5 +gpa=3 +gpa=3.5 PREHOOK: query: explain select c1.name, c1.age, c1.gpa, c2.name, c2.age, c2.gpa from char_tbl1 c1 join char_tbl2 c2 on (c1.gpa = c2.gpa) PREHOOK: type: QUERY POSTHOOK: query: explain select c1.name, c1.age, c1.gpa, c2.name, c2.age, c2.gpa from char_tbl1 c1 join char_tbl2 c2 on (c1.gpa = c2.gpa) POSTHOOK: type: QUERY -Plan optimized by CBO. +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 -Vertex dependency in root stage -Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE) +STAGE PLANS: + Stage: Stage-1 + Tez + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: c1 + Statistics: Num rows: 2 Data size: 204 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: name (type: string), age (type: int), gpa (type: char(50)) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 2 Data size: 204 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col2 (type: char(50)) + sort order: + + Map-reduce partition columns: _col2 (type: char(50)) + Statistics: Num rows: 2 Data size: 204 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: string), _col1 (type: int) + Select Operator + expressions: _col2 (type: char(50)) + outputColumnNames: _col0 + Statistics: Num rows: 2 Data size: 204 Basic stats: COMPLETE Column stats: NONE + Group By Operator + keys: _col0 (type: char(50)) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 2 Data size: 204 Basic stats: COMPLETE Column stats: NONE + Dynamic Partitioning Event Operator + Target Input: c2 + Partition key expr: gpa + Statistics: Num rows: 2 Data size: 204 Basic stats: COMPLETE Column stats: NONE + Target column: gpa + Target Vertex: Map 3 + Execution mode: vectorized + Map 3 + Map Operator Tree: + TableScan + alias: c2 + Statistics: Num rows: 2 Data size: 203 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: name (type: string), age (type: int), gpa (type: char(5)) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 2 Data size: 203 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col2 (type: char(50)) + sort order: + + Map-reduce partition columns: _col2 (type: char(50)) + Statistics: Num rows: 2 Data size: 203 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: string), _col1 (type: int), _col2 (type: char(5)) + Execution mode: vectorized + Reducer 2 + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col2 (type: char(50)) + 1 _col2 (type: char(50)) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Statistics: Num rows: 2 Data size: 224 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 224 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -Stage-0 - Fetch Operator - limit:-1 - Stage-1 - Reducer 2 - File Output Operator [FS_10] - compressed:false - Statistics:Num rows: 2 Data size: 224 Basic stats: COMPLETE Column stats: NONE - table:{"input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat","serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe"} - Merge Join Operator [MERGEJOIN_21] - | condition map:[{"":"Inner Join 0 to 1"}] - | keys:{"0":"_col2 (type: char(50))","1":"_col2 (type: char(50))"} - | outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col5"] - | Statistics:Num rows: 2 Data size: 224 Basic stats: COMPLETE Column stats: NONE - |<-Map 1 [SIMPLE_EDGE] vectorized - | Reduce Output Operator [RS_23] - | key expressions:_col2 (type: char(50)) - | Map-reduce partition columns:_col2 (type: char(50)) - | sort order:+ - | Statistics:Num rows: 2 Data size: 204 Basic stats: COMPLETE Column stats: NONE - | value expressions:_col0 (type: string), _col1 (type: int) - | Select Operator [OP_22] - | outputColumnNames:["_col0","_col1","_col2"] - | Statistics:Num rows: 2 Data size: 204 Basic stats: COMPLETE Column stats: NONE - | TableScan [TS_0] - | alias:c1 - | Statistics:Num rows: 2 Data size: 204 Basic stats: COMPLETE Column stats: NONE - | Dynamic Partitioning Event Operator [EVENT_20] - | Statistics:Num rows: 2 Data size: 204 Basic stats: COMPLETE Column stats: NONE - | Group By Operator [OP_25] - | keys:_col0 (type: char(50)) - | outputColumnNames:["_col0"] - | Statistics:Num rows: 2 Data size: 204 Basic stats: COMPLETE Column stats: NONE - | Select Operator [OP_24] - | outputColumnNames:["_col0"] - | Statistics:Num rows: 2 Data size: 204 Basic stats: COMPLETE Column stats: NONE - | Please refer to the previous Select Operator [OP_22] - |<-Map 3 [SIMPLE_EDGE] vectorized - Reduce Output Operator [RS_27] - key expressions:_col2 (type: char(50)) - Map-reduce partition columns:_col2 (type: char(50)) - sort order:+ - Statistics:Num rows: 2 Data size: 203 Basic stats: COMPLETE Column stats: NONE - value expressions:_col0 (type: string), _col1 (type: int), _col2 (type: char(5)) - Select Operator [OP_26] - outputColumnNames:["_col0","_col1","_col2"] - Statistics:Num rows: 2 Data size: 203 Basic stats: COMPLETE Column stats: NONE - TableScan [TS_2] - alias:c2 - Statistics:Num rows: 2 Data size: 203 Basic stats: COMPLETE Column stats: NONE + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink PREHOOK: query: select c1.name, c1.age, c1.gpa, c2.name, c2.age, c2.gpa from char_tbl1 c1 join char_tbl2 c2 on (c1.gpa = c2.gpa) PREHOOK: type: QUERY PREHOOK: Input: default@char_tbl1 -PREHOOK: Input: default@char_tbl1@gpa=2.5 -PREHOOK: Input: default@char_tbl1@gpa=3.5 +PREHOOK: Input: default@char_tbl1@gpa=2.5 +PREHOOK: Input: default@char_tbl1@gpa=3.5 PREHOOK: Input: default@char_tbl2 -PREHOOK: Input: default@char_tbl2@gpa=3 -PREHOOK: Input: default@char_tbl2@gpa=3.5 +PREHOOK: Input: default@char_tbl2@gpa=3 +PREHOOK: Input: default@char_tbl2@gpa=3.5 #### A masked pattern was here #### POSTHOOK: query: select c1.name, c1.age, c1.gpa, c2.name, c2.age, c2.gpa from char_tbl1 c1 join char_tbl2 c2 on (c1.gpa = c2.gpa) POSTHOOK: type: QUERY POSTHOOK: Input: default@char_tbl1 -POSTHOOK: Input: default@char_tbl1@gpa=2.5 -POSTHOOK: Input: default@char_tbl1@gpa=3.5 +POSTHOOK: Input: default@char_tbl1@gpa=2.5 +POSTHOOK: Input: default@char_tbl1@gpa=3.5 POSTHOOK: Input: default@char_tbl2 -POSTHOOK: Input: default@char_tbl2@gpa=3 -POSTHOOK: Input: default@char_tbl2@gpa=3.5 +POSTHOOK: Input: default@char_tbl2@gpa=3 +POSTHOOK: Input: default@char_tbl2@gpa=3.5 #### A masked pattern was here #### alice underhill 46 3.5 alice underhill 46 3.5 PREHOOK: query: select c1.name, c1.age, c1.gpa, c2.name, c2.age, c2.gpa from char_tbl1 c1 join char_tbl2 c2 on (c1.gpa = c2.gpa) PREHOOK: type: QUERY PREHOOK: Input: default@char_tbl1 -PREHOOK: Input: default@char_tbl1@gpa=2.5 -PREHOOK: Input: default@char_tbl1@gpa=3.5 +PREHOOK: Input: default@char_tbl1@gpa=2.5 +PREHOOK: Input: default@char_tbl1@gpa=3.5 PREHOOK: Input: default@char_tbl2 -PREHOOK: Input: default@char_tbl2@gpa=3 -PREHOOK: Input: default@char_tbl2@gpa=3.5 +PREHOOK: Input: default@char_tbl2@gpa=3 +PREHOOK: Input: default@char_tbl2@gpa=3.5 #### A masked pattern was here #### POSTHOOK: query: select c1.name, c1.age, c1.gpa, c2.name, c2.age, c2.gpa from char_tbl1 c1 join char_tbl2 c2 on (c1.gpa = c2.gpa) POSTHOOK: type: QUERY POSTHOOK: Input: default@char_tbl1 -POSTHOOK: Input: default@char_tbl1@gpa=2.5 -POSTHOOK: Input: default@char_tbl1@gpa=3.5 +POSTHOOK: Input: default@char_tbl1@gpa=2.5 +POSTHOOK: Input: default@char_tbl1@gpa=3.5 POSTHOOK: Input: default@char_tbl2 -POSTHOOK: Input: default@char_tbl2@gpa=3 -POSTHOOK: Input: default@char_tbl2@gpa=3.5 +POSTHOOK: Input: default@char_tbl2@gpa=3 +POSTHOOK: Input: default@char_tbl2@gpa=3.5 #### A masked pattern was here #### alice underhill 46 3.5 alice underhill 46 3.5 diff --git ql/src/test/results/clientpositive/vector_join_nulls.q.out ql/src/test/results/clientpositive/vector_join_nulls.q.out index c1516f2..da39a77 100644 --- ql/src/test/results/clientpositive/vector_join_nulls.q.out +++ ql/src/test/results/clientpositive/vector_join_nulls.q.out @@ -184,6 +184,7 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@myinput1 #### A masked pattern was here #### 3113558 +Warning: Map Join MAPJOIN[28][bigTable=a] in task 'Stage-8:MAPRED' is a cross product PREHOOK: query: SELECT sum(hash(a.key,a.value,b.key,b.value)) FROM myinput1 a LEFT OUTER JOIN myinput1 b RIGHT OUTER JOIN myinput1 c ON a.value = b.value and b.value = c.value PREHOOK: type: QUERY PREHOOK: Input: default@myinput1