http://git-wip-us.apache.org/repos/asf/hive/blob/142367d9/ql/src/test/results/clientpositive/llap/vector_decimal_mapjoin.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/vector_decimal_mapjoin.q.out b/ql/src/test/results/clientpositive/llap/vector_decimal_mapjoin.q.out index cbc4c5d..b66fb9f 100644 --- a/ql/src/test/results/clientpositive/llap/vector_decimal_mapjoin.q.out +++ b/ql/src/test/results/clientpositive/llap/vector_decimal_mapjoin.q.out @@ -1035,8 +1035,8 @@ STAGE PLANS: 0 _col0 (type: decimal(16,2)) 1 _col0 (type: decimal(16,2)) Map Join Vectorization: - bigTableKeyExpressions: ConvertDecimal64ToDecimal(col 0:decimal(16,2)/DECIMAL_64) -> 4:decimal(16,2) - bigTableValueExpressions: ConvertDecimal64ToDecimal(col 0:decimal(16,2)/DECIMAL_64) -> 5:decimal(16,2), ConvertDecimal64ToDecimal(col 1:decimal(14,2)/DECIMAL_64) -> 6:decimal(14,2) + bigTableKeyExpressions: ConvertDecimal64ToDecimal(col 0:decimal(16,2)/DECIMAL_64) -> 3:decimal(16,2) + bigTableValueExpressions: ConvertDecimal64ToDecimal(col 0:decimal(16,2)/DECIMAL_64) -> 4:decimal(16,2), ConvertDecimal64ToDecimal(col 1:decimal(14,2)/DECIMAL_64) -> 5:decimal(14,2) className: VectorMapJoinOperator native: false nativeConditionsMet: hive.mapjoin.optimized.hashtable IS true, hive.vectorized.execution.mapjoin.native.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, One MapJoin Condition IS true, No nullsafe IS true, Small table vectorizes IS true @@ -1072,7 +1072,7 @@ STAGE PLANS: includeColumns: [0, 1] dataColumns: dec:decimal(14,2)/DECIMAL_64, value_dec:decimal(14,2)/DECIMAL_64 partitionColumnCount: 0 - scratchColumnTypeNames: [decimal(14,0), decimal(16,2), decimal(16,2), decimal(14,2)] + scratchColumnTypeNames: [decimal(16,2), decimal(16,2), decimal(14,2), decimal(14,0)] Map 2 Map Operator Tree: TableScan
http://git-wip-us.apache.org/repos/asf/hive/blob/142367d9/ql/src/test/results/clientpositive/llap/vector_outer_reference_windowed.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/vector_outer_reference_windowed.q.out b/ql/src/test/results/clientpositive/llap/vector_outer_reference_windowed.q.out index 17edd47..ba2d9df 100644 --- a/ql/src/test/results/clientpositive/llap/vector_outer_reference_windowed.q.out +++ b/ql/src/test/results/clientpositive/llap/vector_outer_reference_windowed.q.out @@ -503,7 +503,7 @@ STAGE PLANS: aggregators: VectorUDAFSumDecimal64ToDecimal(col 0:decimal(15,2)/DECIMAL_64) -> decimal(25,2) className: VectorGroupByOperator groupByMode: HASH - keyExpressions: col 0:decimal(15,2)/DECIMAL_64, col 1:decimal(15,2)/DECIMAL_64 + keyExpressions: ConvertDecimal64ToDecimal(col 0:decimal(15,2)/DECIMAL_64) -> 3:decimal(15,2), ConvertDecimal64ToDecimal(col 1:decimal(15,2)/DECIMAL_64) -> 4:decimal(15,2) native: false vectorProcessingMode: HASH projectedOutputColumnNums: [0] @@ -539,7 +539,7 @@ STAGE PLANS: includeColumns: [0, 1] dataColumns: c1:decimal(15,2)/DECIMAL_64, c2:decimal(15,2)/DECIMAL_64 partitionColumnCount: 0 - scratchColumnTypeNames: [] + scratchColumnTypeNames: [decimal(15,2), decimal(15,2)] Reducer 2 Execution mode: vectorized, llap Reduce Vectorization: @@ -1801,7 +1801,7 @@ STAGE PLANS: aggregators: VectorUDAFSumDecimal64(col 0:decimal(7,2)/DECIMAL_64) -> decimal(17,2)/DECIMAL_64 className: VectorGroupByOperator groupByMode: HASH - keyExpressions: col 0:decimal(7,2)/DECIMAL_64, col 1:decimal(7,2)/DECIMAL_64 + keyExpressions: ConvertDecimal64ToDecimal(col 0:decimal(7,2)/DECIMAL_64) -> 3:decimal(7,2), ConvertDecimal64ToDecimal(col 1:decimal(7,2)/DECIMAL_64) -> 4:decimal(7,2) native: false vectorProcessingMode: HASH projectedOutputColumnNums: [0] @@ -1837,7 +1837,7 @@ STAGE PLANS: includeColumns: [0, 1] dataColumns: c1:decimal(7,2)/DECIMAL_64, c2:decimal(7,2)/DECIMAL_64 partitionColumnCount: 0 - scratchColumnTypeNames: [] + scratchColumnTypeNames: [decimal(7,2), decimal(7,2)] Reducer 2 Execution mode: vectorized, llap Reduce Vectorization: http://git-wip-us.apache.org/repos/asf/hive/blob/142367d9/ql/src/test/results/clientpositive/llap/vector_udf1.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/vector_udf1.q.out b/ql/src/test/results/clientpositive/llap/vector_udf1.q.out index 5db37eb..2d043e7 100644 --- a/ql/src/test/results/clientpositive/llap/vector_udf1.q.out +++ b/ql/src/test/results/clientpositive/llap/vector_udf1.q.out @@ -71,8 +71,8 @@ STAGE PLANS: Select Vectorization: className: VectorSelectOperator native: true - projectedOutputColumnNums: [9, 10, 13] - selectExpressions: StringGroupConcatColCol(col 0:string, col 1:string) -> 9:string, StringGroupConcatColCol(col 2:varchar(10), col 3:varchar(20)) -> 10:varchar(30), StringGroupColEqualStringGroupColumn(col 11:string, col 12:string)(children: StringGroupConcatColCol(col 0:string, col 1:string) -> 11:string, StringGroupConcatColCol(col 2:varchar(10), col 3:varchar(20)) -> 12:varchar(30)) -> 13:boolean + projectedOutputColumnNums: [9, 10, 14] + selectExpressions: StringGroupConcatColCol(col 0:string, col 1:string) -> 9:string, StringGroupConcatColCol(col 2:varchar(10), col 3:varchar(20)) -> 10:varchar(30), StringGroupColEqualStringGroupColumn(col 11:string, col 13:string)(children: StringGroupConcatColCol(col 0:string, col 1:string) -> 11:string, CastStringGroupToString(col 12:varchar(30))(children: StringGroupConcatColCol(col 2:varchar(10), col 3:varchar(20)) -> 12:varchar(30)) -> 13:string) -> 14:boolean Statistics: Num rows: 1 Data size: 302 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 1 @@ -106,7 +106,7 @@ STAGE PLANS: includeColumns: [0, 1, 2, 3] dataColumns: c1:string, c2:string, c3:varchar(10), c4:varchar(20), d1:string, d2:string, d3:varchar(10), d4:varchar(10) partitionColumnCount: 0 - scratchColumnTypeNames: [string, string, string, string, bigint] + scratchColumnTypeNames: [string, string, string, string, string, bigint] Stage: Stage-0 Fetch Operator @@ -172,8 +172,8 @@ STAGE PLANS: Select Vectorization: className: VectorSelectOperator native: true - projectedOutputColumnNums: [9, 10, 13] - selectExpressions: StringUpper(col 1:string) -> 9:string, StringUpper(col 3:varchar(20)) -> 10:varchar(20), StringGroupColEqualStringGroupColumn(col 11:string, col 12:string)(children: StringUpper(col 1:string) -> 11:string, StringUpper(col 3:varchar(20)) -> 12:varchar(20)) -> 13:boolean + projectedOutputColumnNums: [9, 10, 14] + selectExpressions: StringUpper(col 1:string) -> 9:string, StringUpper(col 3:varchar(20)) -> 10:varchar(20), StringGroupColEqualStringGroupColumn(col 11:string, col 13:string)(children: StringUpper(col 1:string) -> 11:string, CastStringGroupToString(col 12:varchar(20))(children: StringUpper(col 3:varchar(20)) -> 12:varchar(20)) -> 13:string) -> 14:boolean Statistics: Num rows: 1 Data size: 292 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 1 @@ -207,7 +207,7 @@ STAGE PLANS: includeColumns: [1, 3] dataColumns: c1:string, c2:string, c3:varchar(10), c4:varchar(20), d1:string, d2:string, d3:varchar(10), d4:varchar(10) partitionColumnCount: 0 - scratchColumnTypeNames: [string, string, string, string, bigint] + scratchColumnTypeNames: [string, string, string, string, string, bigint] Stage: Stage-0 Fetch Operator @@ -273,8 +273,8 @@ STAGE PLANS: Select Vectorization: className: VectorSelectOperator native: true - projectedOutputColumnNums: [9, 10, 13] - selectExpressions: StringLower(col 1:string) -> 9:string, StringLower(col 3:varchar(20)) -> 10:varchar(20), StringGroupColEqualStringGroupColumn(col 11:string, col 12:string)(children: StringLower(col 1:string) -> 11:string, StringLower(col 3:varchar(20)) -> 12:varchar(20)) -> 13:boolean + projectedOutputColumnNums: [9, 10, 14] + selectExpressions: StringLower(col 1:string) -> 9:string, StringLower(col 3:varchar(20)) -> 10:varchar(20), StringGroupColEqualStringGroupColumn(col 11:string, col 13:string)(children: StringLower(col 1:string) -> 11:string, CastStringGroupToString(col 12:varchar(20))(children: StringLower(col 3:varchar(20)) -> 12:varchar(20)) -> 13:string) -> 14:boolean Statistics: Num rows: 1 Data size: 292 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 1 @@ -308,7 +308,7 @@ STAGE PLANS: includeColumns: [1, 3] dataColumns: c1:string, c2:string, c3:varchar(10), c4:varchar(20), d1:string, d2:string, d3:varchar(10), d4:varchar(10) partitionColumnCount: 0 - scratchColumnTypeNames: [string, string, string, string, bigint] + scratchColumnTypeNames: [string, string, string, string, string, bigint] Stage: Stage-0 Fetch Operator http://git-wip-us.apache.org/repos/asf/hive/blob/142367d9/ql/src/test/results/clientpositive/llap/vectorized_casts.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/vectorized_casts.q.out b/ql/src/test/results/clientpositive/llap/vectorized_casts.q.out index 25dc151..6a72515 100644 --- a/ql/src/test/results/clientpositive/llap/vectorized_casts.q.out +++ b/ql/src/test/results/clientpositive/llap/vectorized_casts.q.out @@ -183,8 +183,8 @@ STAGE PLANS: Select Vectorization: className: VectorSelectOperator native: true - projectedOutputColumnNums: [13, 14, 15, 16, 17, 18, 10, 20, 19, 21, 0, 1, 2, 3, 22, 23, 10, 24, 25, 27, 28, 29, 30, 31, 32, 33, 34, 4, 5, 35, 36, 37, 38, 39, 5, 41, 43, 45, 47, 48, 49, 51, 54, 55, 8, 56, 57, 26, 58, 59, 60, 61, 62, 63, 64, 65, 6, 66, 67, 68, 69, 71, 73] - selectExpressions: CastLongToBooleanViaLongToLong(col 0:tinyint) -> 13:boolean, CastLongToBooleanViaLongToLong(col 1:smallint) -> 14:boolean, CastLongToBooleanViaLongToLong(col 2:int) -> 15:boolean, CastLongToBooleanViaLongToLong(col 3:bigint) -> 16:boolean, CastDoubleToBooleanViaDoubleToLong(col 4:float) -> 17:boolean, CastDoubleToBooleanViaDoubleToLong(col 5:double) -> 18:boolean, CastLongToBooleanViaLongToLong(col 19:bigint)(children: LongColMultiplyLongScalar(col 3:bigint, val 0) -> 19:bigint) -> 20:boolean, CastTimestampToBoolean(col 8:timestamp) -> 19:boolean, CastStringToBoolean(col 6) -> 21:boolean, CastDoubleToLong(col 4:float) -> 22:int, CastDoubleToLong(col 5:double) -> 23:int, CastTimestampToLong(col 8:timestamp) -> 24:int, CastStringToLong(col 6:string) -> 25:int, CastStringToLong(col 26:string)(children: StringSubstrColStartLen(col 6:string, start 0, length 1) -> 26:string) -> 27:int, CastDoubleToLong(col 4:float) -> 28:tinyint, CastDoubleToLo ng(col 4:float) -> 29:smallint, CastDoubleToLong(col 4:float) -> 30:bigint, CastLongToDouble(col 0:tinyint) -> 31:double, CastLongToDouble(col 1:smallint) -> 32:double, CastLongToDouble(col 2:int) -> 33:double, CastLongToDouble(col 3:bigint) -> 34:double, CastLongToDouble(col 10:boolean) -> 35:double, CastTimestampToDouble(col 8:timestamp) -> 36:double, CastStringToDouble(col 6:string) -> 37:double, CastStringToDouble(col 26:string)(children: StringSubstrColStartLen(col 6:string, start 0, length 1) -> 26:string) -> 38:double, CastLongToFloatViaLongToDouble(col 2:int) -> 39:float, CastMillisecondsLongToTimestamp(col 0:tinyint) -> 41:timestamp, CastMillisecondsLongToTimestamp(col 1:smallint) -> 43:timestamp, CastMillisecondsLongToTimestamp(col 2:int) -> 45:timestamp, CastMillisecondsLongToTimestamp(col 3:bigint) -> 47:timestamp, CastDoubleToTimestamp(col 4:float) -> 48:timestamp, CastDoubleToTimestamp(col 5:double) -> 49:timestamp, CastMillisecondsLongToTimestamp(col 10:boolean) -> 51 :timestamp, CastMillisecondsLongToTimestamp(col 52:bigint)(children: LongColMultiplyLongScalar(col 3:bigint, val 0) -> 52:bigint) -> 54:timestamp, CastDateToTimestamp(col 52:date)(children: CastTimestampToDate(col 8:timestamp) -> 52:date) -> 55:timestamp, CastStringToTimestamp(col 6:string) -> 56:timestamp, CastStringToTimestamp(col 26:string)(children: StringSubstrColStartLen(col 6:string, start 0, length 1) -> 26:string) -> 57:timestamp, CastLongToString(col 0:tinyint) -> 26:string, CastLongToString(col 1:smallint) -> 58:string, CastLongToString(col 2:int) -> 59:string, CastLongToString(col 3:bigint) -> 60:string, CastFloatToString(col 4:float) -> 61:string, CastDoubleToString(col 5:double) -> 62:string, CastBooleanToStringViaLongToString(col 10:boolean) -> 63:string, CastLongToString(col 52:bigint)(children: LongColMultiplyLongScalar(col 3:bigint, val 0) -> 52:bigint) -> 64:string, CastTimestampToString(col 8:timestamp) -> 65:string, CastStringGroupToChar(col 6:string, maxLength 10) -> 66:char(10), CastStringGroupToVarChar(col 6:string, maxLength 10) -> 67:varchar(10), CastLongToFloatViaLongToDouble(col 52:int)(children: CastDoubleToLong(col 4:float) -> 52:int) -> 68:float, CastLongToDouble(col 52:int)(children: LongColMultiplyLongScalar(col 2:int, val 2) -> 52:int) -> 69:double, CastDoubleToString(col 70:double)(children: FuncSinDoubleToDouble(col 4:float) -> 70:double) -> 71:string, DoubleColAddDoubleColumn(col 70:double, col 72:double)(children: CastLongToFloatViaLongToDouble(col 2:int) -> 70:float, CastLongToDouble(col 10:boolean) -> 72:double) -> 73:double + projectedOutputColumnNums: [13, 14, 15, 16, 17, 18, 10, 20, 19, 21, 0, 1, 2, 3, 22, 23, 10, 24, 25, 27, 28, 29, 30, 31, 32, 33, 34, 4, 5, 35, 36, 37, 38, 39, 5, 41, 43, 45, 47, 48, 49, 51, 54, 55, 8, 56, 57, 26, 58, 59, 60, 61, 62, 63, 64, 65, 6, 67, 68, 69, 70, 66, 73] + selectExpressions: CastLongToBooleanViaLongToLong(col 0:tinyint) -> 13:boolean, CastLongToBooleanViaLongToLong(col 1:smallint) -> 14:boolean, CastLongToBooleanViaLongToLong(col 2:int) -> 15:boolean, CastLongToBooleanViaLongToLong(col 3:bigint) -> 16:boolean, CastDoubleToBooleanViaDoubleToLong(col 4:float) -> 17:boolean, CastDoubleToBooleanViaDoubleToLong(col 5:double) -> 18:boolean, CastLongToBooleanViaLongToLong(col 19:bigint)(children: LongColMultiplyLongScalar(col 3:bigint, val 0) -> 19:bigint) -> 20:boolean, CastTimestampToBoolean(col 8:timestamp) -> 19:boolean, CastStringToBoolean(col 6) -> 21:boolean, CastDoubleToLong(col 4:float) -> 22:int, CastDoubleToLong(col 5:double) -> 23:int, CastTimestampToLong(col 8:timestamp) -> 24:int, CastStringToLong(col 6:string) -> 25:int, CastStringToLong(col 26:string)(children: StringSubstrColStartLen(col 6:string, start 0, length 1) -> 26:string) -> 27:int, CastDoubleToLong(col 4:float) -> 28:tinyint, CastDoubleToLo ng(col 4:float) -> 29:smallint, CastDoubleToLong(col 4:float) -> 30:bigint, CastLongToDouble(col 0:tinyint) -> 31:double, CastLongToDouble(col 1:smallint) -> 32:double, CastLongToDouble(col 2:int) -> 33:double, CastLongToDouble(col 3:bigint) -> 34:double, CastLongToDouble(col 10:boolean) -> 35:double, CastTimestampToDouble(col 8:timestamp) -> 36:double, CastStringToDouble(col 6:string) -> 37:double, CastStringToDouble(col 26:string)(children: StringSubstrColStartLen(col 6:string, start 0, length 1) -> 26:string) -> 38:double, CastLongToFloatViaLongToDouble(col 2:int) -> 39:float, CastMillisecondsLongToTimestamp(col 0:tinyint) -> 41:timestamp, CastMillisecondsLongToTimestamp(col 1:smallint) -> 43:timestamp, CastMillisecondsLongToTimestamp(col 2:int) -> 45:timestamp, CastMillisecondsLongToTimestamp(col 3:bigint) -> 47:timestamp, CastDoubleToTimestamp(col 4:float) -> 48:timestamp, CastDoubleToTimestamp(col 5:double) -> 49:timestamp, CastMillisecondsLongToTimestamp(col 10:boolean) -> 51 :timestamp, CastMillisecondsLongToTimestamp(col 52:bigint)(children: LongColMultiplyLongScalar(col 3:bigint, val 0) -> 52:bigint) -> 54:timestamp, CastDateToTimestamp(col 52:date)(children: CastTimestampToDate(col 8:timestamp) -> 52:date) -> 55:timestamp, CastStringToTimestamp(col 6:string) -> 56:timestamp, CastStringToTimestamp(col 26:string)(children: StringSubstrColStartLen(col 6:string, start 0, length 1) -> 26:string) -> 57:timestamp, CastLongToString(col 0:tinyint) -> 26:string, CastLongToString(col 1:smallint) -> 58:string, CastLongToString(col 2:int) -> 59:string, CastLongToString(col 3:bigint) -> 60:string, CastFloatToString(col 4:float) -> 61:string, CastDoubleToString(col 5:double) -> 62:string, CastBooleanToStringViaLongToString(col 10:boolean) -> 63:string, CastLongToString(col 52:bigint)(children: LongColMultiplyLongScalar(col 3:bigint, val 0) -> 52:bigint) -> 64:string, CastTimestampToString(col 8:timestamp) -> 65:string, CastStringGroupToString(col 66:char(10))(child ren: CastStringGroupToChar(col 6:string, maxLength 10) -> 66:char(10)) -> 67:string, CastStringGroupToString(col 66:varchar(10))(children: CastStringGroupToVarChar(col 6:string, maxLength 10) -> 66:varchar(10)) -> 68:string, CastLongToFloatViaLongToDouble(col 52:int)(children: CastDoubleToLong(col 4:float) -> 52:int) -> 69:float, CastLongToDouble(col 52:int)(children: LongColMultiplyLongScalar(col 2:int, val 2) -> 52:int) -> 70:double, CastDoubleToString(col 71:double)(children: FuncSinDoubleToDouble(col 4:float) -> 71:double) -> 66:string, DoubleColAddDoubleColumn(col 71:double, col 72:double)(children: CastLongToFloatViaLongToDouble(col 2:int) -> 71:float, CastLongToDouble(col 10:boolean) -> 72:double) -> 73:double Statistics: Num rows: 6144 Data size: 16362860 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false @@ -212,7 +212,7 @@ STAGE PLANS: includeColumns: [0, 1, 2, 3, 4, 5, 6, 8, 10] dataColumns: ctinyint:tinyint, csmallint:smallint, cint:int, cbigint:bigint, cfloat:float, cdouble:double, cstring1:string, cstring2:string, ctimestamp1:timestamp, ctimestamp2:timestamp, cboolean1:boolean, cboolean2:boolean partitionColumnCount: 0 - scratchColumnTypeNames: [bigint, bigint, bigint, bigint, bigint, bigint, bigint, bigint, bigint, bigint, bigint, bigint, bigint, string, bigint, bigint, bigint, bigint, double, double, double, double, double, double, double, double, double, timestamp, timestamp, timestamp, timestamp, timestamp, timestamp, timestamp, timestamp, timestamp, timestamp, timestamp, timestamp, bigint, timestamp, timestamp, timestamp, timestamp, timestamp, string, string, string, string, string, string, string, string, string, string, double, double, double, string, double, double] + scratchColumnTypeNames: [bigint, bigint, bigint, bigint, bigint, bigint, bigint, bigint, bigint, bigint, bigint, bigint, bigint, string, bigint, bigint, bigint, bigint, double, double, double, double, double, double, double, double, double, timestamp, timestamp, timestamp, timestamp, timestamp, timestamp, timestamp, timestamp, timestamp, timestamp, timestamp, timestamp, bigint, timestamp, timestamp, timestamp, timestamp, timestamp, string, string, string, string, string, string, string, string, string, string, string, double, double, double, double, double] Stage: Stage-0 Fetch Operator http://git-wip-us.apache.org/repos/asf/hive/blob/142367d9/ql/src/test/results/clientpositive/llap/vectorized_mapjoin3.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/vectorized_mapjoin3.q.out b/ql/src/test/results/clientpositive/llap/vectorized_mapjoin3.q.out index 6b945a6..8efe78d 100644 --- a/ql/src/test/results/clientpositive/llap/vectorized_mapjoin3.q.out +++ b/ql/src/test/results/clientpositive/llap/vectorized_mapjoin3.q.out @@ -147,12 +147,13 @@ STAGE PLANS: 1 _col0 (type: int) Map Join Vectorization: bigTableKeyColumnNums: [1] - bigTableRetainedColumnNums: [0] - bigTableValueColumnNums: [0] + bigTableRetainedColumnNums: [3] + bigTableValueColumnNums: [3] + bigTableValueExpressions: ConvertDecimal64ToDecimal(col 0:decimal(8,1)/DECIMAL_64) -> 3:decimal(8,1) className: VectorMapJoinInnerBigOnlyLongOperator native: true nativeConditionsMet: hive.mapjoin.optimized.hashtable IS true, hive.vectorized.execution.mapjoin.native.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, One MapJoin Condition IS true, No nullsafe IS true, Small table vectorizes IS true, Optimized Table and Supports Key Types IS true - projectedOutputColumnNums: [0] + projectedOutputColumnNums: [3] outputColumnNames: _col0 input vertices: 1 Reducer 3 @@ -183,7 +184,7 @@ STAGE PLANS: includeColumns: [0, 1] dataColumns: decimal0801_col:decimal(8,1)/DECIMAL_64, int_col_1:int partitionColumnCount: 0 - scratchColumnTypeNames: [] + scratchColumnTypeNames: [decimal(8,1)] Map 2 Map Operator Tree: TableScan @@ -351,12 +352,13 @@ STAGE PLANS: 1 _col0 (type: int) Map Join Vectorization: bigTableKeyColumnNums: [1] - bigTableRetainedColumnNums: [0] - bigTableValueColumnNums: [0] + bigTableRetainedColumnNums: [3] + bigTableValueColumnNums: [3] + bigTableValueExpressions: ConvertDecimal64ToDecimal(col 0:decimal(8,1)/DECIMAL_64) -> 3:decimal(8,1) className: VectorMapJoinInnerBigOnlyLongOperator native: true nativeConditionsMet: hive.mapjoin.optimized.hashtable IS true, hive.vectorized.execution.mapjoin.native.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, One MapJoin Condition IS true, No nullsafe IS true, Small table vectorizes IS true, Optimized Table and Supports Key Types IS true - projectedOutputColumnNums: [0] + projectedOutputColumnNums: [3] outputColumnNames: _col0 input vertices: 1 Reducer 3 @@ -387,7 +389,7 @@ STAGE PLANS: includeColumns: [0, 1] dataColumns: decimal0801_col:decimal(8,1)/DECIMAL_64, int_col_1:int partitionColumnCount: 0 - scratchColumnTypeNames: [] + scratchColumnTypeNames: [decimal(8,1)] Map 2 Map Operator Tree: TableScan @@ -555,12 +557,13 @@ STAGE PLANS: 1 _col0 (type: int) Map Join Vectorization: bigTableKeyColumnNums: [1] - bigTableRetainedColumnNums: [0] - bigTableValueColumnNums: [0] + bigTableRetainedColumnNums: [3] + bigTableValueColumnNums: [3] + bigTableValueExpressions: ConvertDecimal64ToDecimal(col 0:decimal(8,1)/DECIMAL_64) -> 3:decimal(8,1) className: VectorMapJoinInnerBigOnlyLongOperator native: true nativeConditionsMet: hive.mapjoin.optimized.hashtable IS true, hive.vectorized.execution.mapjoin.native.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, One MapJoin Condition IS true, No nullsafe IS true, Small table vectorizes IS true, Optimized Table and Supports Key Types IS true - projectedOutputColumnNums: [0] + projectedOutputColumnNums: [3] outputColumnNames: _col0 input vertices: 1 Reducer 3 @@ -591,7 +594,7 @@ STAGE PLANS: includeColumns: [0, 1] dataColumns: decimal0801_col:decimal(8,1)/DECIMAL_64, int_col_1:int partitionColumnCount: 0 - scratchColumnTypeNames: [] + scratchColumnTypeNames: [decimal(8,1)] Map 2 Map Operator Tree: TableScan http://git-wip-us.apache.org/repos/asf/hive/blob/142367d9/ql/src/test/results/clientpositive/perf/spark/query1.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/spark/query1.q.out b/ql/src/test/results/clientpositive/perf/spark/query1.q.out index 5cbab38..19f24ba 100644 --- a/ql/src/test/results/clientpositive/perf/spark/query1.q.out +++ b/ql/src/test/results/clientpositive/perf/spark/query1.q.out @@ -1,4 +1,4 @@ -PREHOOK: query: explain vectorization expression +PREHOOK: query: explain with customer_total_return as (select sr_customer_sk as ctr_customer_sk ,sr_store_sk as ctr_store_sk @@ -22,7 +22,7 @@ and ctr1.ctr_customer_sk = c_customer_sk order by c_customer_id limit 100 PREHOOK: type: QUERY -POSTHOOK: query: explain vectorization expression +POSTHOOK: query: explain with customer_total_return as (select sr_customer_sk as ctr_customer_sk ,sr_store_sk as ctr_store_sk @@ -46,10 +46,6 @@ and ctr1.ctr_customer_sk = c_customer_sk order by c_customer_id limit 100 POSTHOOK: type: QUERY -PLAN VECTORIZATION: - enabled: true - enabledConditionsMet: [hive.vectorized.execution.enabled IS true] - STAGE DEPENDENCIES: Stage-2 is a root stage Stage-1 depends on stages: Stage-2 @@ -66,40 +62,18 @@ STAGE PLANS: alias: store filterExpr: ((s_state = 'NM') and s_store_sk is not null) (type: boolean) Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE - TableScan Vectorization: - native: true Filter Operator - Filter Vectorization: - className: VectorFilterOperator - native: true - predicateExpression: FilterExprAndExpr(children: FilterStringGroupColEqualStringScalar(col 24:string, val NM), SelectColumnIsNotNull(col 0:int)) predicate: ((s_state = 'NM') and s_store_sk is not null) (type: boolean) Statistics: Num rows: 852 Data size: 1628138 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: s_store_sk (type: int) outputColumnNames: _col0 - Select Vectorization: - className: VectorSelectOperator - native: true - projectedOutputColumnNums: [0] Statistics: Num rows: 852 Data size: 1628138 Basic stats: COMPLETE Column stats: NONE Spark HashTable Sink Operator - Spark Hash Table Sink Vectorization: - className: VectorSparkHashTableSinkOperator - native: true keys: 0 _col1 (type: int) 1 _col0 (type: int) Execution mode: vectorized - Map Vectorization: - enabled: true - enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true - inputFormatFeatureSupport: [DECIMAL_64] - featureSupportInUse: [DECIMAL_64] - inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat - allNative: true - usesVectorUDFAdaptor: false - vectorized: true Local Work: Map Reduce Local Work @@ -121,219 +95,99 @@ STAGE PLANS: alias: store_returns filterExpr: (sr_returned_date_sk is not null and sr_store_sk is not null and sr_customer_sk is not null) (type: boolean) Statistics: Num rows: 57591150 Data size: 4462194832 Basic stats: COMPLETE Column stats: NONE - TableScan Vectorization: - native: true Filter Operator - Filter Vectorization: - className: VectorFilterOperator - native: true - predicateExpression: FilterExprAndExpr(children: SelectColumnIsNotNull(col 0:int), SelectColumnIsNotNull(col 7:int), SelectColumnIsNotNull(col 3:int)) predicate: (sr_customer_sk is not null and sr_returned_date_sk is not null and sr_store_sk is not null) (type: boolean) Statistics: Num rows: 57591150 Data size: 4462194832 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: sr_returned_date_sk (type: int), sr_customer_sk (type: int), sr_store_sk (type: int), sr_fee (type: decimal(7,2)) outputColumnNames: _col0, _col1, _col2, _col3 - Select Vectorization: - className: VectorSelectOperator - native: true - projectedOutputColumnNums: [0, 3, 7, 14] Statistics: Num rows: 57591150 Data size: 4462194832 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Reduce Sink Vectorization: - className: VectorReduceSinkLongOperator - native: true - nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true Statistics: Num rows: 57591150 Data size: 4462194832 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: int), _col2 (type: int), _col3 (type: decimal(7,2)) Execution mode: vectorized - Map Vectorization: - enabled: true - enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true - inputFormatFeatureSupport: [DECIMAL_64] - featureSupportInUse: [DECIMAL_64] - inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat - allNative: true - usesVectorUDFAdaptor: false - vectorized: true Map 10 Map Operator Tree: TableScan alias: store_returns filterExpr: (sr_returned_date_sk is not null and sr_store_sk is not null) (type: boolean) Statistics: Num rows: 57591150 Data size: 4462194832 Basic stats: COMPLETE Column stats: NONE - TableScan Vectorization: - native: true Filter Operator - Filter Vectorization: - className: VectorFilterOperator - native: true - predicateExpression: FilterExprAndExpr(children: SelectColumnIsNotNull(col 0:int), SelectColumnIsNotNull(col 7:int)) predicate: (sr_returned_date_sk is not null and sr_store_sk is not null) (type: boolean) Statistics: Num rows: 57591150 Data size: 4462194832 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: sr_returned_date_sk (type: int), sr_customer_sk (type: int), sr_store_sk (type: int), sr_fee (type: decimal(7,2)) outputColumnNames: _col0, _col1, _col2, _col3 - Select Vectorization: - className: VectorSelectOperator - native: true - projectedOutputColumnNums: [0, 3, 7, 14] Statistics: Num rows: 57591150 Data size: 4462194832 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Reduce Sink Vectorization: - className: VectorReduceSinkLongOperator - native: true - nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true Statistics: Num rows: 57591150 Data size: 4462194832 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: int), _col2 (type: int), _col3 (type: decimal(7,2)) Execution mode: vectorized - Map Vectorization: - enabled: true - enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true - inputFormatFeatureSupport: [DECIMAL_64] - featureSupportInUse: [DECIMAL_64] - inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat - allNative: true - usesVectorUDFAdaptor: false - vectorized: true Map 13 Map Operator Tree: TableScan alias: date_dim filterExpr: ((d_year = 2000) and d_date_sk is not null) (type: boolean) Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - TableScan Vectorization: - native: true Filter Operator - Filter Vectorization: - className: VectorFilterOperator - native: true - predicateExpression: FilterExprAndExpr(children: FilterLongColEqualLongScalar(col 6:int, val 2000), SelectColumnIsNotNull(col 0:int)) predicate: ((d_year = 2000) and d_date_sk is not null) (type: boolean) Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: d_date_sk (type: int) outputColumnNames: _col0 - Select Vectorization: - className: VectorSelectOperator - native: true - projectedOutputColumnNums: [0] Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Reduce Sink Vectorization: - className: VectorReduceSinkLongOperator - native: true - nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized - Map Vectorization: - enabled: true - enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true - inputFormatFeatureSupport: [DECIMAL_64] - featureSupportInUse: [DECIMAL_64] - inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat - allNative: true - usesVectorUDFAdaptor: false - vectorized: true Map 7 Map Operator Tree: TableScan alias: date_dim filterExpr: ((d_year = 2000) and d_date_sk is not null) (type: boolean) Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - TableScan Vectorization: - native: true Filter Operator - Filter Vectorization: - className: VectorFilterOperator - native: true - predicateExpression: FilterExprAndExpr(children: FilterLongColEqualLongScalar(col 6:int, val 2000), SelectColumnIsNotNull(col 0:int)) predicate: ((d_year = 2000) and d_date_sk is not null) (type: boolean) Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: d_date_sk (type: int) outputColumnNames: _col0 - Select Vectorization: - className: VectorSelectOperator - native: true - projectedOutputColumnNums: [0] Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Reduce Sink Vectorization: - className: VectorReduceSinkLongOperator - native: true - nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized - Map Vectorization: - enabled: true - enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true - inputFormatFeatureSupport: [DECIMAL_64] - featureSupportInUse: [DECIMAL_64] - inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat - allNative: true - usesVectorUDFAdaptor: false - vectorized: true Map 9 Map Operator Tree: TableScan alias: customer filterExpr: c_customer_sk is not null (type: boolean) Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE - TableScan Vectorization: - native: true Filter Operator - Filter Vectorization: - className: VectorFilterOperator - native: true - predicateExpression: SelectColumnIsNotNull(col 0:int) predicate: c_customer_sk is not null (type: boolean) Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: c_customer_sk (type: int), c_customer_id (type: string) outputColumnNames: _col0, _col1 - Select Vectorization: - className: VectorSelectOperator - native: true - projectedOutputColumnNums: [0, 1] Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Reduce Sink Vectorization: - className: VectorReduceSinkLongOperator - native: true - nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Execution mode: vectorized - Map Vectorization: - enabled: true - enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true - inputFormatFeatureSupport: [DECIMAL_64] - featureSupportInUse: [DECIMAL_64] - inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat - allNative: true - usesVectorUDFAdaptor: false - vectorized: true Reducer 11 - Reduce Vectorization: - enabled: true - enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true - notVectorizedReason: Tagging not supported - vectorized: false Reduce Operator Tree: Join Operator condition map: @@ -357,23 +211,9 @@ STAGE PLANS: value expressions: _col2 (type: decimal(17,2)) Reducer 12 Execution mode: vectorized - Reduce Vectorization: - enabled: true - enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true - allNative: false - usesVectorUDFAdaptor: false - vectorized: true Reduce Operator Tree: Group By Operator aggregations: sum(VALUE._col0) - Group By Vectorization: - aggregators: VectorUDAFSumDecimal(col 2:decimal(17,2)) -> decimal(17,2) - className: VectorGroupByOperator - groupByMode: MERGEPARTIAL - keyExpressions: col 0:int, col 1:int - native: false - vectorProcessingMode: MERGE_PARTIAL - projectedOutputColumnNums: [0] keys: KEY._col0 (type: int), KEY._col1 (type: int) mode: mergepartial outputColumnNames: _col0, _col1, _col2 @@ -381,21 +221,9 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col2 (type: decimal(17,2)) outputColumnNames: _col1, _col2 - Select Vectorization: - className: VectorSelectOperator - native: true - projectedOutputColumnNums: [0, 2] Statistics: Num rows: 31675133 Data size: 2454207210 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: sum(_col2), count(_col2) - Group By Vectorization: - aggregators: VectorUDAFSumDecimal(col 2:decimal(17,2)) -> decimal(27,2), VectorUDAFCount(col 2:decimal(17,2)) -> bigint - className: VectorGroupByOperator - groupByMode: COMPLETE - keyExpressions: col 0:int - native: false - vectorProcessingMode: STREAMING - projectedOutputColumnNums: [0, 1] keys: _col1 (type: int) mode: complete outputColumnNames: _col0, _col1, _col2 @@ -403,28 +231,14 @@ STAGE PLANS: Select Operator expressions: ((_col1 / _col2) * 1.2) (type: decimal(38,11)), _col0 (type: int) outputColumnNames: _col0, _col1 - Select Vectorization: - className: VectorSelectOperator - native: true - projectedOutputColumnNums: [5, 0] - selectExpressions: DecimalColMultiplyDecimalScalar(col 4:decimal(38,13), val 1.2)(children: DecimalColDivideDecimalColumn(col 1:decimal(27,2), col 3:decimal(19,0))(children: CastLongToDecimal(col 2:bigint) -> 3:decimal(19,0)) -> 4:decimal(38,13)) -> 5:decimal(38,11) Statistics: Num rows: 15837566 Data size: 1227103566 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col1 (type: int) sort order: + Map-reduce partition columns: _col1 (type: int) - Reduce Sink Vectorization: - className: VectorReduceSinkLongOperator - native: true - nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true Statistics: Num rows: 15837566 Data size: 1227103566 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: decimal(38,11)) Reducer 2 - Reduce Vectorization: - enabled: true - enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true - notVectorizedReason: Tagging not supported - vectorized: false Reduce Operator Tree: Join Operator condition map: @@ -450,23 +264,9 @@ STAGE PLANS: Execution mode: vectorized Local Work: Map Reduce Local Work - Reduce Vectorization: - enabled: true - enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true - allNative: false - usesVectorUDFAdaptor: false - vectorized: true Reduce Operator Tree: Group By Operator aggregations: sum(VALUE._col0) - Group By Vectorization: - aggregators: VectorUDAFSumDecimal(col 2:decimal(17,2)) -> decimal(17,2) - className: VectorGroupByOperator - groupByMode: MERGEPARTIAL - keyExpressions: col 0:int, col 1:int - native: false - vectorProcessingMode: MERGE_PARTIAL - projectedOutputColumnNums: [0] keys: KEY._col0 (type: int), KEY._col1 (type: int) mode: mergepartial outputColumnNames: _col0, _col1, _col2 @@ -474,10 +274,6 @@ STAGE PLANS: Select Operator expressions: _col1 (type: int), _col0 (type: int), _col2 (type: decimal(17,2)) outputColumnNames: _col0, _col1, _col2 - Select Vectorization: - className: VectorSelectOperator - native: true - projectedOutputColumnNums: [1, 0, 2] Statistics: Num rows: 31675133 Data size: 2454207210 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: @@ -485,10 +281,6 @@ STAGE PLANS: keys: 0 _col1 (type: int) 1 _col0 (type: int) - Map Join Vectorization: - className: VectorMapJoinInnerBigOnlyLongOperator - native: true - nativeConditionsMet: hive.mapjoin.optimized.hashtable IS true, hive.vectorized.execution.mapjoin.native.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true, One MapJoin Condition IS true, No nullsafe IS true, Small table vectorizes IS true, Optimized Table and Supports Key Types IS true outputColumnNames: _col0, _col1, _col2 input vertices: 1 Map 8 @@ -497,18 +289,9 @@ STAGE PLANS: key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Reduce Sink Vectorization: - className: VectorReduceSinkLongOperator - native: true - nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true Statistics: Num rows: 34842647 Data size: 2699627989 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: int), _col2 (type: decimal(17,2)) Reducer 4 - Reduce Vectorization: - enabled: true - enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true - notVectorizedReason: Tagging not supported - vectorized: false Reduce Operator Tree: Join Operator condition map: @@ -525,11 +308,6 @@ STAGE PLANS: Statistics: Num rows: 88000001 Data size: 75681779077 Basic stats: COMPLETE Column stats: NONE value expressions: _col2 (type: decimal(17,2)), _col6 (type: string) Reducer 5 - Reduce Vectorization: - enabled: true - enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true - notVectorizedReason: Tagging not supported - vectorized: false Reduce Operator Tree: Join Operator condition map: @@ -553,32 +331,16 @@ STAGE PLANS: TopN Hash Memory Usage: 0.1 Reducer 6 Execution mode: vectorized - Reduce Vectorization: - enabled: true - enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true - allNative: false - usesVectorUDFAdaptor: false - vectorized: true Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string) outputColumnNames: _col0 - Select Vectorization: - className: VectorSelectOperator - native: true - projectedOutputColumnNums: [0] Statistics: Num rows: 32266667 Data size: 27749985689 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 100 - Limit Vectorization: - className: VectorLimitOperator - native: true Statistics: Num rows: 100 Data size: 86000 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - File Sink Vectorization: - className: VectorFileSinkOperator - native: false Statistics: Num rows: 100 Data size: 86000 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat
