You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@hive.apache.org by jc...@apache.org on 2019/01/04 00:24:15 UTC
[16/35] hive git commit: HIVE-16957: Support CTAS for auto gather
column stats (Jesus Camacho Rodriguez, reviewed by Ashutosh Chauhan)
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/vector_case_when_1.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/vector_case_when_1.q.out b/ql/src/test/results/clientpositive/llap/vector_case_when_1.q.out
index 5f94d60..6529758 100644
--- a/ql/src/test/results/clientpositive/llap/vector_case_when_1.q.out
+++ b/ql/src/test/results/clientpositive/llap/vector_case_when_1.q.out
@@ -204,7 +204,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: lineitem_test
- Statistics: Num rows: 101 Data size: 57327 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 101 Data size: 58277 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:l_orderkey:int, 1:l_partkey:int, 2:l_suppkey:int, 3:l_linenumber:int, 4:l_quantity:int, 5:l_extendedprice:double, 6:l_discount:double, 7:l_tax:decimal(10,2)/DECIMAL_64, 8:l_returnflag:char(1), 9:l_linestatus:char(1), 10:l_shipdate:date, 11:l_commitdate:date, 12:l_receiptdate:date, 13:l_shipinstruct:varchar(20), 14:l_shipmode:char(10), 15:l_comment:string, 16:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -216,13 +216,13 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [4, 21, 26, 31, 35, 39, 43, 45, 47, 49, 51, 53, 55, 59, 62, 65, 68]
selectExpressions: VectorUDFAdaptor(CASE WHEN ((l_quantity = 1)) THEN ('Single') WHEN ((l_quantity = 2)) THEN ('Two') WHEN ((l_quantity < 10)) THEN ('Some') WHEN ((l_quantity < 100)) THEN ('Many') ELSE ('Huge number') END)(children: LongColEqualLongScalar(col 4:int, val 1) -> 17:boolean, LongColEqualLongScalar(col 4:int, val 2) -> 18:boolean, LongColLessLongScalar(col 4:int, val 10) -> 19:boolean, LongColLessLongScalar(col 4:int, val 100) -> 20:boolean) -> 21:string, VectorUDFAdaptor(CASE WHEN ((l_quantity = 1)) THEN ('Single') WHEN ((l_quantity = 2)) THEN ('Two') WHEN ((l_quantity < 10)) THEN ('Some') WHEN ((l_quantity < 100)) THEN ('Many') ELSE (null) END)(children: LongColEqualLongScalar(col 4:int, val 1) -> 22:boolean, LongColEqualLongScalar(col 4:int, val 2) -> 23:boolean, LongColLessLongScalar(col 4:int, val 10) -> 24:boolean, LongColLessLongScalar(col 4:int, val 100) -> 25:boolean) -> 26:string, VectorUDFAdaptor(CASE WHEN ((l_quantity = 1)) THEN ('Sing
le') WHEN ((l_quantity = 2)) THEN ('Two') WHEN ((l_quantity < 10)) THEN ('Some') WHEN ((l_quantity < 100)) THEN (null) ELSE (null) END)(children: LongColEqualLongScalar(col 4:int, val 1) -> 27:boolean, LongColEqualLongScalar(col 4:int, val 2) -> 28:boolean, LongColLessLongScalar(col 4:int, val 10) -> 29:boolean, LongColLessLongScalar(col 4:int, val 100) -> 30:boolean) -> 31:string, IfExprLongColumnLongColumn(col 32:boolean, col 33:date, col 34:date)(children: StringGroupColEqualCharScalar(col 14:char(10), val SHIP) -> 32:boolean, VectorUDFDateAddColScalar(col 10:date, val 10) -> 33:date, VectorUDFDateAddColScalar(col 10:date, val 5) -> 34:date) -> 35:date, VectorUDFAdaptor(CASE WHEN ((l_returnflag = 'N')) THEN ((l_extendedprice * (1.0D - l_discount))) ELSE (0) END)(children: StringGroupColEqualCharScalar(col 8:char(1), val N) -> 36:boolean, DoubleColMultiplyDoubleColumn(col 5:double, col 37:double)(children: DoubleScalarSubtractDoubleColumn(val 1.0, col 6:double) -> 37:double) -> 38
:double) -> 39:double, VectorUDFAdaptor(CASE WHEN ((l_returnflag = 'N')) THEN ((l_extendedprice * (1.0D - l_discount))) ELSE (0.0D) END)(children: StringGroupColEqualCharScalar(col 8:char(1), val N) -> 40:boolean, DoubleColMultiplyDoubleColumn(col 5:double, col 41:double)(children: DoubleScalarSubtractDoubleColumn(val 1.0, col 6:double) -> 41:double) -> 42:double) -> 43:double, VectorUDFAdaptor(if((CAST( l_shipinstruct AS STRING) = 'DELIVER IN PERSON'), null, l_tax))(children: StringGroupColEqualStringScalar(col 13:string, val DELIVER IN PERSON)(children: col 13:varchar(20)) -> 44:boolean) -> 45:decimal(10,2), VectorUDFAdaptor(if((CAST( l_shipinstruct AS STRING) = 'TAKE BACK RETURN'), l_tax, null))(children: StringGroupColEqualStringScalar(col 13:string, val TAKE BACK RETURN)(children: col 13:varchar(20)) -> 46:boolean) -> 47:decimal(10,2), VectorUDFAdaptor(if((CAST( l_shipinstruct AS STRING) = 'DELIVER IN PERSON'), 0, l_tax))(children: StringGroupColEqualStringScalar(col 13:string,
val DELIVER IN PERSON)(children: col 13:varchar(20)) -> 48:boolean) -> 49:decimal(12,2), VectorUDFAdaptor(if((CAST( l_shipinstruct AS STRING) = 'TAKE BACK RETURN'), l_tax, 0))(children: StringGroupColEqualStringScalar(col 13:string, val TAKE BACK RETURN)(children: col 13:varchar(20)) -> 50:boolean) -> 51:decimal(12,2), IfExprDecimal64ScalarDecimal64Column(col 52:boolean, decimal64Val 0, decimalVal 0, col 7:decimal(10,2)/DECIMAL_64)(children: StringGroupColEqualStringScalar(col 13:string, val DELIVER IN PERSON)(children: col 13:varchar(20)) -> 52:boolean) -> 53:decimal(10,2)/DECIMAL_64, IfExprDecimal64ColumnDecimal64Scalar(col 54:boolean, col 7:decimal(10,2)/DECIMAL_64, decimal64Val 0, decimalVal 0)(children: StringGroupColEqualStringScalar(col 13:string, val TAKE BACK RETURN)(children: col 13:varchar(20)) -> 54:boolean) -> 55:decimal(10,2)/DECIMAL_64, IfExprTimestampColumnColumn(col 56:boolean, col 57:timestampcol 58:timestamp)(children: LongColGreaterLongScalar(col 1:int, val 30)
-> 56:boolean, CastDateToTimestamp(col 12:date) -> 57:timestamp, CastDateToTimestamp(col 11:date) -> 58:timestamp) -> 59:timestamp, VectorUDFAdaptor(if((l_suppkey > 10000), datediff(l_receiptdate, l_commitdate), null))(children: LongColGreaterLongScalar(col 2:int, val 10000) -> 60:boolean, VectorUDFDateDiffColCol(col 12:date, col 11:date) -> 61:int) -> 62:int, VectorUDFAdaptor(if((l_suppkey > 10000), null, datediff(l_receiptdate, l_commitdate)))(children: LongColGreaterLongScalar(col 2:int, val 10000) -> 63:boolean, VectorUDFDateDiffColCol(col 12:date, col 11:date) -> 64:int) -> 65:int, IfExprLongScalarLongScalar(col 67:boolean, val 14245, val 14609)(children: LongColGreaterLongScalar(col 66:int, val 100)(children: LongColModuloLongScalar(col 2:int, val 500) -> 66:int) -> 67:boolean) -> 68:date
- Statistics: Num rows: 101 Data size: 57327 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 101 Data size: 141804 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 101 Data size: 57327 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 101 Data size: 141804 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -541,7 +541,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: lineitem_test
- Statistics: Num rows: 101 Data size: 57327 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 101 Data size: 58277 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:l_orderkey:int, 1:l_partkey:int, 2:l_suppkey:int, 3:l_linenumber:int, 4:l_quantity:int, 5:l_extendedprice:double, 6:l_discount:double, 7:l_tax:decimal(10,2)/DECIMAL_64, 8:l_returnflag:char(1), 9:l_linestatus:char(1), 10:l_shipdate:date, 11:l_commitdate:date, 12:l_receiptdate:date, 13:l_shipinstruct:varchar(20), 14:l_shipmode:char(10), 15:l_comment:string, 16:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -553,13 +553,13 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [4, 24, 33, 40, 44, 49, 53, 55, 57, 59, 61, 63, 65, 69, 72, 75, 78]
selectExpressions: IfExprStringScalarStringGroupColumn(col 17:boolean, val Singlecol 23:string)(children: LongColEqualLongScalar(col 4:int, val 1) -> 17:boolean, IfExprStringScalarStringGroupColumn(col 18:boolean, val Twocol 22:string)(children: LongColEqualLongScalar(col 4:int, val 2) -> 18:boolean, IfExprStringScalarStringGroupColumn(col 19:boolean, val Somecol 21:string)(children: LongColLessLongScalar(col 4:int, val 10) -> 19:boolean, IfExprStringScalarStringScalar(col 20:boolean, val Many, val Huge number)(children: LongColLessLongScalar(col 4:int, val 100) -> 20:boolean) -> 21:string) -> 22:string) -> 23:string) -> 24:string, IfExprStringScalarStringGroupColumn(col 25:boolean, val Singlecol 32:string)(children: LongColEqualLongScalar(col 4:int, val 1) -> 25:boolean, IfExprStringScalarStringGroupColumn(col 26:boolean, val Twocol 31:string)(children: LongColEqualLongScalar(col 4:int, val 2) -> 26:boolean, IfExprStringScalarStringGroupColumn(col 27:boolean
, val Somecol 30:string)(children: LongColLessLongScalar(col 4:int, val 10) -> 27:boolean, IfExprColumnNull(col 28:boolean, col 29:string, null)(children: LongColLessLongScalar(col 4:int, val 100) -> 28:boolean, ConstantVectorExpression(val Many) -> 29:string) -> 30:string) -> 31:string) -> 32:string) -> 33:string, IfExprStringScalarStringGroupColumn(col 34:boolean, val Singlecol 39:string)(children: LongColEqualLongScalar(col 4:int, val 1) -> 34:boolean, IfExprStringScalarStringGroupColumn(col 35:boolean, val Twocol 38:string)(children: LongColEqualLongScalar(col 4:int, val 2) -> 35:boolean, IfExprStringScalarStringGroupColumn(col 36:boolean, val Somecol 37:string)(children: LongColLessLongScalar(col 4:int, val 10) -> 36:boolean, IfExprNullNull(null, null) -> 37:string) -> 38:string) -> 39:string) -> 40:string, IfExprLongColumnLongColumn(col 41:boolean, col 42:date, col 43:date)(children: StringGroupColEqualCharScalar(col 14:char(10), val SHIP) -> 41:boolean, VectorUDFDateAddColSca
lar(col 10:date, val 10) -> 42:date, VectorUDFDateAddColScalar(col 10:date, val 5) -> 43:date) -> 44:date, IfExprDoubleColumnDoubleColumn(col 45:boolean, col 47:doublecol 48:double)(children: StringGroupColEqualCharScalar(col 8:char(1), val N) -> 45:boolean, DoubleColMultiplyDoubleColumn(col 5:double, col 46:double)(children: DoubleScalarSubtractDoubleColumn(val 1.0, col 6:double) -> 46:double) -> 47:double, ConstantVectorExpression(val 0.0) -> 48:double) -> 49:double, IfExprDoubleColumnDoubleScalar(col 50:boolean, col 52:double, val 0.0)(children: StringGroupColEqualCharScalar(col 8:char(1), val N) -> 50:boolean, DoubleColMultiplyDoubleColumn(col 5:double, col 51:double)(children: DoubleScalarSubtractDoubleColumn(val 1.0, col 6:double) -> 51:double) -> 52:double) -> 53:double, IfExprNullColumn(col 54:boolean, null, col 79)(children: StringGroupColEqualStringScalar(col 13:string, val DELIVER IN PERSON)(children: col 13:varchar(20)) -> 54:boolean, ConvertDecimal64ToDecimal(col 7:deci
mal(10,2)/DECIMAL_64) -> 79:decimal(10,2)) -> 55:decimal(10,2), IfExprColumnNull(col 56:boolean, col 80:decimal(10,2), null)(children: StringGroupColEqualStringScalar(col 13:string, val TAKE BACK RETURN)(children: col 13:varchar(20)) -> 56:boolean, ConvertDecimal64ToDecimal(col 7:decimal(10,2)/DECIMAL_64) -> 80:decimal(10,2)) -> 57:decimal(10,2), VectorUDFAdaptor(if((CAST( l_shipinstruct AS STRING) = 'DELIVER IN PERSON'), 0, l_tax))(children: StringGroupColEqualStringScalar(col 13:string, val DELIVER IN PERSON)(children: col 13:varchar(20)) -> 58:boolean) -> 59:decimal(12,2), VectorUDFAdaptor(if((CAST( l_shipinstruct AS STRING) = 'TAKE BACK RETURN'), l_tax, 0))(children: StringGroupColEqualStringScalar(col 13:string, val TAKE BACK RETURN)(children: col 13:varchar(20)) -> 60:boolean) -> 61:decimal(12,2), IfExprDecimal64ScalarDecimal64Column(col 62:boolean, decimal64Val 0, decimalVal 0, col 7:decimal(10,2)/DECIMAL_64)(children: StringGroupColEqualStringScalar(col 13:string, val DELIVE
R IN PERSON)(children: col 13:varchar(20)) -> 62:boolean) -> 63:decimal(10,2)/DECIMAL_64, IfExprDecimal64ColumnDecimal64Scalar(col 64:boolean, col 7:decimal(10,2)/DECIMAL_64, decimal64Val 0, decimalVal 0)(children: StringGroupColEqualStringScalar(col 13:string, val TAKE BACK RETURN)(children: col 13:varchar(20)) -> 64:boolean) -> 65:decimal(10,2)/DECIMAL_64, IfExprTimestampColumnColumn(col 66:boolean, col 67:timestampcol 68:timestamp)(children: LongColGreaterLongScalar(col 1:int, val 30) -> 66:boolean, CastDateToTimestamp(col 12:date) -> 67:timestamp, CastDateToTimestamp(col 11:date) -> 68:timestamp) -> 69:timestamp, IfExprColumnNull(col 70:boolean, col 71:int, null)(children: LongColGreaterLongScalar(col 2:int, val 10000) -> 70:boolean, VectorUDFDateDiffColCol(col 12:date, col 11:date) -> 71:int) -> 72:int, IfExprNullColumn(col 73:boolean, null, col 74)(children: LongColGreaterLongScalar(col 2:int, val 10000) -> 73:boolean, VectorUDFDateDiffColCol(col 12:date, col 11:date) -> 74:in
t) -> 75:int, IfExprLongScalarLongScalar(col 77:boolean, val 14245, val 14609)(children: LongColGreaterLongScalar(col 76:int, val 100)(children: LongColModuloLongScalar(col 2:int, val 500) -> 76:int) -> 77:boolean) -> 78:date
- Statistics: Num rows: 101 Data size: 57327 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 101 Data size: 141804 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 101 Data size: 57327 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 101 Data size: 141804 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -878,7 +878,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: lineitem_test
- Statistics: Num rows: 101 Data size: 57327 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 101 Data size: 58277 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:l_orderkey:int, 1:l_partkey:int, 2:l_suppkey:int, 3:l_linenumber:int, 4:l_quantity:int, 5:l_extendedprice:double, 6:l_discount:double, 7:l_tax:decimal(10,2)/DECIMAL_64, 8:l_returnflag:char(1), 9:l_linestatus:char(1), 10:l_shipdate:date, 11:l_commitdate:date, 12:l_receiptdate:date, 13:l_shipinstruct:varchar(20), 14:l_shipmode:char(10), 15:l_comment:string, 16:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -890,13 +890,13 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [4, 27, 39, 49, 53, 58, 63, 65, 67, 72, 77, 79, 81, 85, 88, 91, 94]
selectExpressions: IfExprColumnCondExpr(col 17:boolean, col 18:stringcol 26:string)(children: LongColEqualLongScalar(col 4:int, val 1) -> 17:boolean, ConstantVectorExpression(val Single) -> 18:string, IfExprColumnCondExpr(col 19:boolean, col 20:stringcol 25:string)(children: LongColEqualLongScalar(col 4:int, val 2) -> 19:boolean, ConstantVectorExpression(val Two) -> 20:string, IfExprColumnCondExpr(col 21:boolean, col 22:stringcol 24:string)(children: LongColLessLongScalar(col 4:int, val 10) -> 21:boolean, ConstantVectorExpression(val Some) -> 22:string, IfExprStringScalarStringScalar(col 23:boolean, val Many, val Huge number)(children: LongColLessLongScalar(col 4:int, val 100) -> 23:boolean) -> 24:string) -> 25:string) -> 26:string) -> 27:string, IfExprColumnCondExpr(col 28:boolean, col 29:stringcol 38:string)(children: LongColEqualLongScalar(col 4:int, val 1) -> 28:boolean, ConstantVectorExpression(val Single) -> 29:string, IfExprColumnCondExpr(col 30:boolea
n, col 31:stringcol 37:string)(children: LongColEqualLongScalar(col 4:int, val 2) -> 30:boolean, ConstantVectorExpression(val Two) -> 31:string, IfExprColumnCondExpr(col 32:boolean, col 33:stringcol 36:string)(children: LongColLessLongScalar(col 4:int, val 10) -> 32:boolean, ConstantVectorExpression(val Some) -> 33:string, IfExprColumnNull(col 34:boolean, col 35:string, null)(children: LongColLessLongScalar(col 4:int, val 100) -> 34:boolean, ConstantVectorExpression(val Many) -> 35:string) -> 36:string) -> 37:string) -> 38:string) -> 39:string, IfExprColumnCondExpr(col 40:boolean, col 41:stringcol 48:string)(children: LongColEqualLongScalar(col 4:int, val 1) -> 40:boolean, ConstantVectorExpression(val Single) -> 41:string, IfExprColumnCondExpr(col 42:boolean, col 43:stringcol 47:string)(children: LongColEqualLongScalar(col 4:int, val 2) -> 42:boolean, ConstantVectorExpression(val Two) -> 43:string, IfExprColumnCondExpr(col 44:boolean, col 45:stringcol 46:string)(children: LongColLes
sLongScalar(col 4:int, val 10) -> 44:boolean, ConstantVectorExpression(val Some) -> 45:string, IfExprNullNull(null, null) -> 46:string) -> 47:string) -> 48:string) -> 49:string, IfExprCondExprCondExpr(col 50:boolean, col 51:datecol 52:date)(children: StringGroupColEqualCharScalar(col 14:char(10), val SHIP) -> 50:boolean, VectorUDFDateAddColScalar(col 10:date, val 10) -> 51:date, VectorUDFDateAddColScalar(col 10:date, val 5) -> 52:date) -> 53:date, IfExprCondExprCondExpr(col 54:boolean, col 56:doublecol 57:double)(children: StringGroupColEqualCharScalar(col 8:char(1), val N) -> 54:boolean, DoubleColMultiplyDoubleColumn(col 5:double, col 55:double)(children: DoubleScalarSubtractDoubleColumn(val 1.0, col 6:double) -> 55:double) -> 56:double, ConstantVectorExpression(val 0.0) -> 57:double) -> 58:double, IfExprCondExprColumn(col 59:boolean, col 61:double, col 62:double)(children: StringGroupColEqualCharScalar(col 8:char(1), val N) -> 59:boolean, DoubleColMultiplyDoubleColumn(col 5:double
, col 60:double)(children: DoubleScalarSubtractDoubleColumn(val 1.0, col 6:double) -> 60:double) -> 61:double, ConstantVectorExpression(val 0.0) -> 62:double) -> 63:double, IfExprNullColumn(col 64:boolean, null, col 95)(children: StringGroupColEqualStringScalar(col 13:string, val DELIVER IN PERSON)(children: col 13:varchar(20)) -> 64:boolean, ConvertDecimal64ToDecimal(col 7:decimal(10,2)/DECIMAL_64) -> 95:decimal(10,2)) -> 65:decimal(10,2), IfExprColumnNull(col 66:boolean, col 96:decimal(10,2), null)(children: StringGroupColEqualStringScalar(col 13:string, val TAKE BACK RETURN)(children: col 13:varchar(20)) -> 66:boolean, ConvertDecimal64ToDecimal(col 7:decimal(10,2)/DECIMAL_64) -> 96:decimal(10,2)) -> 67:decimal(10,2), VectorUDFAdaptor(if((CAST( l_shipinstruct AS STRING) = 'DELIVER IN PERSON'), 0, l_tax))(children: StringGroupColEqualStringScalar(col 13:string, val DELIVER IN PERSON)(children: col 13:varchar(20)) -> 71:boolean) -> 72:decimal(12,2), VectorUDFAdaptor(if((CAST( l_ship
instruct AS STRING) = 'TAKE BACK RETURN'), l_tax, 0))(children: StringGroupColEqualStringScalar(col 13:string, val TAKE BACK RETURN)(children: col 13:varchar(20)) -> 76:boolean) -> 77:decimal(12,2), IfExprDecimal64ScalarDecimal64Column(col 78:boolean, decimal64Val 0, decimalVal 0, col 7:decimal(10,2)/DECIMAL_64)(children: StringGroupColEqualStringScalar(col 13:string, val DELIVER IN PERSON)(children: col 13:varchar(20)) -> 78:boolean) -> 79:decimal(10,2)/DECIMAL_64, IfExprDecimal64ColumnDecimal64Scalar(col 80:boolean, col 7:decimal(10,2)/DECIMAL_64, decimal64Val 0, decimalVal 0)(children: StringGroupColEqualStringScalar(col 13:string, val TAKE BACK RETURN)(children: col 13:varchar(20)) -> 80:boolean) -> 81:decimal(10,2)/DECIMAL_64, IfExprCondExprCondExpr(col 82:boolean, col 83:timestampcol 84:timestamp)(children: LongColGreaterLongScalar(col 1:int, val 30) -> 82:boolean, CastDateToTimestamp(col 12:date) -> 83:timestamp, CastDateToTimestamp(col 11:date) -> 84:timestamp) -> 85:timesta
mp, IfExprCondExprNull(col 86:boolean, col 87:int, null)(children: LongColGreaterLongScalar(col 2:int, val 10000) -> 86:boolean, VectorUDFDateDiffColCol(col 12:date, col 11:date) -> 87:int) -> 88:int, IfExprNullCondExpr(col 89:boolean, null, col 90:int)(children: LongColGreaterLongScalar(col 2:int, val 10000) -> 89:boolean, VectorUDFDateDiffColCol(col 12:date, col 11:date) -> 90:int) -> 91:int, IfExprLongScalarLongScalar(col 93:boolean, val 14245, val 14609)(children: LongColGreaterLongScalar(col 92:int, val 100)(children: LongColModuloLongScalar(col 2:int, val 500) -> 92:int) -> 93:boolean) -> 94:date
- Statistics: Num rows: 101 Data size: 57327 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 101 Data size: 141804 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 101 Data size: 57327 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 101 Data size: 141804 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/vector_char_mapjoin1.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/vector_char_mapjoin1.q.out b/ql/src/test/results/clientpositive/llap/vector_char_mapjoin1.q.out
index 23024d3..d6f01ae 100644
--- a/ql/src/test/results/clientpositive/llap/vector_char_mapjoin1.q.out
+++ b/ql/src/test/results/clientpositive/llap/vector_char_mapjoin1.q.out
@@ -154,7 +154,7 @@ STAGE PLANS:
TableScan
alias: a
filterExpr: c2 is not null (type: boolean)
- Statistics: Num rows: 3 Data size: 294 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 273 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Filter Operator
@@ -163,7 +163,7 @@ STAGE PLANS:
native: true
predicateExpression: SelectColumnIsNotNull(col 1:char(10))
predicate: c2 is not null (type: boolean)
- Statistics: Num rows: 3 Data size: 294 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 273 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: c1 (type: int), c2 (type: char(10))
outputColumnNames: _col0, _col1
@@ -171,7 +171,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1]
- Statistics: Num rows: 3 Data size: 294 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 273 Basic stats: COMPLETE Column stats: COMPLETE
Map Join Operator
condition map:
Inner Join 0 to 1
@@ -186,7 +186,7 @@ STAGE PLANS:
outputColumnNames: _col0, _col1, _col2, _col3
input vertices:
1 Map 3
- Statistics: Num rows: 3 Data size: 323 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 728 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
@@ -194,7 +194,7 @@ STAGE PLANS:
className: VectorReduceSinkObjectHashOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez 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: 3 Data size: 323 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 728 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: char(10)), _col2 (type: int), _col3 (type: char(10))
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -212,7 +212,7 @@ STAGE PLANS:
TableScan
alias: b
filterExpr: c2 is not null (type: boolean)
- Statistics: Num rows: 3 Data size: 294 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 273 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Filter Operator
@@ -221,7 +221,7 @@ STAGE PLANS:
native: true
predicateExpression: SelectColumnIsNotNull(col 1:char(10))
predicate: c2 is not null (type: boolean)
- Statistics: Num rows: 3 Data size: 294 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 273 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: c1 (type: int), c2 (type: char(10))
outputColumnNames: _col0, _col1
@@ -229,7 +229,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1]
- Statistics: Num rows: 3 Data size: 294 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 273 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col1 (type: char(10))
sort order: +
@@ -238,7 +238,7 @@ STAGE PLANS:
className: VectorReduceSinkStringOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez 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: 3 Data size: 294 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 273 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: int)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -267,13 +267,13 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1, 2, 3]
- Statistics: Num rows: 3 Data size: 323 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 728 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 3 Data size: 323 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 728 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -321,8 +321,8 @@ STAGE PLANS:
Tez
#### A masked pattern was here ####
Edges:
- Map 2 <- Map 1 (BROADCAST_EDGE)
- Reducer 3 <- Map 2 (SIMPLE_EDGE)
+ Map 1 <- Map 3 (BROADCAST_EDGE)
+ Reducer 2 <- Map 1 (SIMPLE_EDGE)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -330,7 +330,7 @@ STAGE PLANS:
TableScan
alias: a
filterExpr: c2 is not null (type: boolean)
- Statistics: Num rows: 3 Data size: 294 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 273 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Filter Operator
@@ -339,7 +339,7 @@ STAGE PLANS:
native: true
predicateExpression: SelectColumnIsNotNull(col 1:char(10))
predicate: c2 is not null (type: boolean)
- Statistics: Num rows: 3 Data size: 294 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 273 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: c1 (type: int), c2 (type: char(10))
outputColumnNames: _col0, _col1
@@ -347,17 +347,31 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1]
- Statistics: Num rows: 3 Data size: 294 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col1 (type: char(20))
- sort order: +
- Map-reduce partition columns: _col1 (type: char(20))
- Reduce Sink Vectorization:
- className: VectorReduceSinkStringOperator
+ Statistics: Num rows: 3 Data size: 273 Basic stats: COMPLETE Column stats: COMPLETE
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col1 (type: char(20))
+ 1 _col1 (type: char(20))
+ Map Join Vectorization:
+ className: VectorMapJoinInnerStringOperator
native: true
- nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez 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: 3 Data size: 294 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col0 (type: int)
+ 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
+ hashTableImplementationType: OPTIMIZED
+ outputColumnNames: _col0, _col1, _col2, _col3
+ input vertices:
+ 1 Map 3
+ Statistics: Num rows: 4 Data size: 728 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col0 (type: int)
+ sort order: +
+ Reduce Sink Vectorization:
+ className: VectorReduceSinkObjectHashOperator
+ native: true
+ nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez 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: 4 Data size: 728 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col1 (type: char(10)), _col2 (type: int), _col3 (type: char(20))
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -369,12 +383,12 @@ STAGE PLANS:
allNative: true
usesVectorUDFAdaptor: false
vectorized: true
- Map 2
+ Map 3
Map Operator Tree:
TableScan
alias: b
filterExpr: c2 is not null (type: boolean)
- Statistics: Num rows: 3 Data size: 324 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 273 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Filter Operator
@@ -383,7 +397,7 @@ STAGE PLANS:
native: true
predicateExpression: SelectColumnIsNotNull(col 1:char(20))
predicate: c2 is not null (type: boolean)
- Statistics: Num rows: 3 Data size: 324 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 273 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: c1 (type: int), c2 (type: char(20))
outputColumnNames: _col0, _col1
@@ -391,31 +405,17 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1]
- Statistics: Num rows: 3 Data size: 324 Basic stats: COMPLETE Column stats: NONE
- Map Join Operator
- condition map:
- Inner Join 0 to 1
- keys:
- 0 _col1 (type: char(20))
- 1 _col1 (type: char(20))
- Map Join Vectorization:
- className: VectorMapJoinInnerStringOperator
+ Statistics: Num rows: 3 Data size: 273 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col1 (type: char(20))
+ sort order: +
+ Map-reduce partition columns: _col1 (type: char(20))
+ Reduce Sink Vectorization:
+ className: VectorReduceSinkStringOperator
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
- hashTableImplementationType: OPTIMIZED
- outputColumnNames: _col0, _col1, _col2, _col3
- input vertices:
- 0 Map 1
- Statistics: Num rows: 3 Data size: 323 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: int)
- sort order: +
- Reduce Sink Vectorization:
- className: VectorReduceSinkObjectHashOperator
- native: true
- nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez 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: 3 Data size: 323 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col1 (type: char(10)), _col2 (type: int), _col3 (type: char(20))
+ nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez 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: 3 Data size: 273 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col0 (type: int)
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -427,7 +427,7 @@ STAGE PLANS:
allNative: true
usesVectorUDFAdaptor: false
vectorized: true
- Reducer 3
+ Reducer 2
Execution mode: vectorized, llap
Reduce Vectorization:
enabled: true
@@ -443,13 +443,13 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1, 2, 3]
- Statistics: Num rows: 3 Data size: 323 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 728 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 3 Data size: 323 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 728 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -499,8 +499,8 @@ STAGE PLANS:
Tez
#### A masked pattern was here ####
Edges:
- Map 2 <- Map 1 (BROADCAST_EDGE)
- Reducer 3 <- Map 2 (SIMPLE_EDGE)
+ Map 1 <- Map 3 (BROADCAST_EDGE)
+ Reducer 2 <- Map 1 (SIMPLE_EDGE)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -508,7 +508,7 @@ STAGE PLANS:
TableScan
alias: a
filterExpr: c2 is not null (type: boolean)
- Statistics: Num rows: 3 Data size: 294 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 273 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Filter Operator
@@ -517,7 +517,7 @@ STAGE PLANS:
native: true
predicateExpression: SelectColumnIsNotNull(col 1:char(10))
predicate: c2 is not null (type: boolean)
- Statistics: Num rows: 3 Data size: 294 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 273 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: c1 (type: int), c2 (type: char(10)), CAST( c2 AS STRING) (type: string)
outputColumnNames: _col0, _col1, _col2
@@ -525,17 +525,39 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1, 1]
- Statistics: Num rows: 3 Data size: 294 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col2 (type: string)
- sort order: +
- Map-reduce partition columns: _col2 (type: string)
- Reduce Sink Vectorization:
- className: VectorReduceSinkStringOperator
+ Statistics: Num rows: 3 Data size: 825 Basic stats: COMPLETE Column stats: COMPLETE
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col2 (type: string)
+ 1 _col1 (type: string)
+ Map Join Vectorization:
+ className: VectorMapJoinInnerStringOperator
native: true
- nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez 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: 3 Data size: 294 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col0 (type: int), _col1 (type: char(10))
+ 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
+ hashTableImplementationType: OPTIMIZED
+ outputColumnNames: _col0, _col1, _col3, _col4
+ input vertices:
+ 1 Map 3
+ Statistics: Num rows: 3 Data size: 549 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: char(10)), _col3 (type: int), _col4 (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumnNums: [0, 1, 3, 1]
+ Statistics: Num rows: 3 Data size: 549 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col0 (type: int)
+ sort order: +
+ Reduce Sink Vectorization:
+ className: VectorReduceSinkObjectHashOperator
+ native: true
+ nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez 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: 3 Data size: 549 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col1 (type: char(10)), _col2 (type: int), _col3 (type: string)
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -547,12 +569,12 @@ STAGE PLANS:
allNative: true
usesVectorUDFAdaptor: false
vectorized: true
- Map 2
+ Map 3
Map Operator Tree:
TableScan
alias: b
filterExpr: c2 is not null (type: boolean)
- Statistics: Num rows: 3 Data size: 564 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 276 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Filter Operator
@@ -561,7 +583,7 @@ STAGE PLANS:
native: true
predicateExpression: SelectColumnIsNotNull(col 1:string)
predicate: c2 is not null (type: boolean)
- Statistics: Num rows: 3 Data size: 564 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 276 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: c1 (type: int), c2 (type: string)
outputColumnNames: _col0, _col1
@@ -569,39 +591,17 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1]
- Statistics: Num rows: 3 Data size: 564 Basic stats: COMPLETE Column stats: NONE
- Map Join Operator
- condition map:
- Inner Join 0 to 1
- keys:
- 0 _col2 (type: string)
- 1 _col1 (type: string)
- Map Join Vectorization:
- className: VectorMapJoinInnerStringOperator
+ Statistics: Num rows: 3 Data size: 276 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col1 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col1 (type: string)
+ Reduce Sink Vectorization:
+ className: VectorReduceSinkStringOperator
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
- hashTableImplementationType: OPTIMIZED
- outputColumnNames: _col0, _col1, _col3, _col4
- input vertices:
- 0 Map 1
- Statistics: Num rows: 3 Data size: 323 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col0 (type: int), _col1 (type: char(10)), _col3 (type: int), _col4 (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3
- Select Vectorization:
- className: VectorSelectOperator
- native: true
- projectedOutputColumnNums: [3, 4, 0, 1]
- Statistics: Num rows: 3 Data size: 323 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: int)
- sort order: +
- Reduce Sink Vectorization:
- className: VectorReduceSinkObjectHashOperator
- native: true
- nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez 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: 3 Data size: 323 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col1 (type: char(10)), _col2 (type: int), _col3 (type: string)
+ nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez 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: 3 Data size: 276 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col0 (type: int)
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -613,7 +613,7 @@ STAGE PLANS:
allNative: true
usesVectorUDFAdaptor: false
vectorized: true
- Reducer 3
+ Reducer 2
Execution mode: vectorized, llap
Reduce Vectorization:
enabled: true
@@ -629,13 +629,13 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1, 2, 3]
- Statistics: Num rows: 3 Data size: 323 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 549 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 3 Data size: 323 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 549 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/vector_char_varchar_1.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/vector_char_varchar_1.q.out b/ql/src/test/results/clientpositive/llap/vector_char_varchar_1.q.out
index d2db6db..e919a70 100644
--- a/ql/src/test/results/clientpositive/llap/vector_char_varchar_1.q.out
+++ b/ql/src/test/results/clientpositive/llap/vector_char_varchar_1.q.out
@@ -46,7 +46,7 @@ PLAN VECTORIZATION:
STAGE DEPENDENCIES:
Stage-1 is a root stage
Stage-2 depends on stages: Stage-1
- Stage-4 depends on stages: Stage-2, Stage-0
+ Stage-4 depends on stages: Stage-0, Stage-2
Stage-3 depends on stages: Stage-4
Stage-0 depends on stages: Stage-1
@@ -54,52 +54,68 @@ STAGE PLANS:
Stage: Stage-1
Tez
#### A masked pattern was here ####
+ Edges:
+ Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE)
+#### A masked pattern was here ####
Vertices:
Map 1
Map Operator Tree:
TableScan
alias: varchar_table
Statistics: Num rows: 6 Data size: 564 Basic stats: COMPLETE Column stats: NONE
- TableScan Vectorization:
- native: true
- vectorizationSchemaColumns: [0:vs:varchar(10), 1:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
Select Operator
expressions: length(vs) (type: int), reverse(vs) (type: string)
outputColumnNames: _col0, _col1
- Select Vectorization:
- className: VectorSelectOperator
- native: true
- projectedOutputColumnNums: [2, 3]
- selectExpressions: StringLength(col 0:varchar(10)) -> 2:int, VectorUDFAdaptor(reverse(vs)) -> 3:string
Statistics: Num rows: 6 Data size: 564 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- File Sink Vectorization:
- className: VectorFileSinkOperator
- native: false
Statistics: Num rows: 6 Data size: 564 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
name: default.varchar_ctas_1
- Execution mode: vectorized, llap
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: string)
+ outputColumnNames: col1, col2
+ Statistics: Num rows: 6 Data size: 564 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: compute_stats(col1, 'hll'), compute_stats(col2, 'hll')
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 958 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 958 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
+ Execution mode: llap
LLAP IO: no inputs
Map Vectorization:
enabled: true
enabledConditionsMet: hive.vectorized.use.vector.serde.deserialize IS true
- inputFormatFeatureSupport: [DECIMAL_64]
- featureSupportInUse: [DECIMAL_64]
inputFileFormats: org.apache.hadoop.mapred.TextInputFormat
- allNative: false
- usesVectorUDFAdaptor: true
- vectorized: true
- rowBatchContext:
- dataColumnCount: 1
- includeColumns: [0]
- dataColumns: vs:varchar(10)
- partitionColumnCount: 0
- scratchColumnTypeNames: [bigint, string]
+ notVectorizedReason: Aggregation Function expression for GROUPBY operator: UDF compute_stats not supported
+ vectorized: false
+ Reducer 2
+ Execution mode: llap
+ Reduce Vectorization:
+ enabled: true
+ enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true
+ notVectorizedReason: Aggregation Function expression for GROUPBY operator: UDF compute_stats not supported
+ vectorized: false
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 974 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 974 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
Stage: Stage-2
Dependency Collection
@@ -116,6 +132,10 @@ STAGE PLANS:
Stage: Stage-3
Stats Work
Basic Stats Work:
+ Column Stats Desc:
+ Columns: _c0, _c1
+ Column Types: int, string
+ Table: default.varchar_ctas_1
Stage: Stage-0
Move Operator
@@ -199,7 +219,7 @@ PLAN VECTORIZATION:
STAGE DEPENDENCIES:
Stage-1 is a root stage
Stage-2 depends on stages: Stage-1
- Stage-4 depends on stages: Stage-2, Stage-0
+ Stage-4 depends on stages: Stage-0, Stage-2
Stage-3 depends on stages: Stage-4
Stage-0 depends on stages: Stage-1
@@ -207,52 +227,68 @@ STAGE PLANS:
Stage: Stage-1
Tez
#### A masked pattern was here ####
+ Edges:
+ Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE)
+#### A masked pattern was here ####
Vertices:
Map 1
Map Operator Tree:
TableScan
alias: char_table
Statistics: Num rows: 6 Data size: 564 Basic stats: COMPLETE Column stats: NONE
- TableScan Vectorization:
- native: true
- vectorizationSchemaColumns: [0:vs:char(10), 1:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
Select Operator
expressions: length(vs) (type: int), reverse(vs) (type: string)
outputColumnNames: _col0, _col1
- Select Vectorization:
- className: VectorSelectOperator
- native: true
- projectedOutputColumnNums: [2, 3]
- selectExpressions: StringLength(col 0:char(10)) -> 2:int, VectorUDFAdaptor(reverse(vs)) -> 3:string
Statistics: Num rows: 6 Data size: 564 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- File Sink Vectorization:
- className: VectorFileSinkOperator
- native: false
Statistics: Num rows: 6 Data size: 564 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
name: default.char_ctas_1
- Execution mode: vectorized, llap
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: string)
+ outputColumnNames: col1, col2
+ Statistics: Num rows: 6 Data size: 564 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: compute_stats(col1, 'hll'), compute_stats(col2, 'hll')
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 958 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 958 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
+ Execution mode: llap
LLAP IO: no inputs
Map Vectorization:
enabled: true
enabledConditionsMet: hive.vectorized.use.vector.serde.deserialize IS true
- inputFormatFeatureSupport: [DECIMAL_64]
- featureSupportInUse: [DECIMAL_64]
inputFileFormats: org.apache.hadoop.mapred.TextInputFormat
- allNative: false
- usesVectorUDFAdaptor: true
- vectorized: true
- rowBatchContext:
- dataColumnCount: 1
- includeColumns: [0]
- dataColumns: vs:char(10)
- partitionColumnCount: 0
- scratchColumnTypeNames: [bigint, string]
+ notVectorizedReason: Aggregation Function expression for GROUPBY operator: UDF compute_stats not supported
+ vectorized: false
+ Reducer 2
+ Execution mode: llap
+ Reduce Vectorization:
+ enabled: true
+ enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true
+ notVectorizedReason: Aggregation Function expression for GROUPBY operator: UDF compute_stats not supported
+ vectorized: false
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 974 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 974 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
Stage: Stage-2
Dependency Collection
@@ -269,6 +305,10 @@ STAGE PLANS:
Stage: Stage-3
Stats Work
Basic Stats Work:
+ Column Stats Desc:
+ Columns: _c0, _c1
+ Column Types: int, string
+ Table: default.char_ctas_1
Stage: Stage-0
Move Operator
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/vector_count.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/vector_count.q.out b/ql/src/test/results/clientpositive/llap/vector_count.q.out
index a0f301e..2ca934e 100644
--- a/ql/src/test/results/clientpositive/llap/vector_count.q.out
+++ b/ql/src/test/results/clientpositive/llap/vector_count.q.out
@@ -71,22 +71,22 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: abcd
- Statistics: Num rows: 7 Data size: 112 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 7 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: a (type: int), b (type: int), c (type: int), d (type: int)
outputColumnNames: a, b, c, d
- Statistics: Num rows: 7 Data size: 112 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 7 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count(DISTINCT b), count(DISTINCT c), sum(d)
keys: a (type: int), b (type: int), c (type: int)
mode: hash
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
- Statistics: Num rows: 7 Data size: 112 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 108 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int)
sort order: +++
Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 7 Data size: 112 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 108 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col5 (type: bigint)
Execution mode: llap
LLAP IO: all inputs
@@ -109,10 +109,10 @@ STAGE PLANS:
keys: KEY._col0 (type: int)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 3 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 84 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 3 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 84 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -164,21 +164,21 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: abcd
- Statistics: Num rows: 7 Data size: 112 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 7 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: a (type: int), b (type: int), c (type: int), d (type: int)
outputColumnNames: a, b, c, d
- Statistics: Num rows: 7 Data size: 112 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 7 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count(), count(a), count(b), count(c), count(d), count(DISTINCT a), count(DISTINCT b), count(DISTINCT c), count(DISTINCT d), count(DISTINCT a, b), count(DISTINCT b, c), count(DISTINCT c, d), count(DISTINCT a, d), count(DISTINCT a, c), count(DISTINCT b, d), count(DISTINCT a, b, c), count(DISTINCT b, c, d), count(DISTINCT a, c, d), count(DISTINCT a, b, d), count(DISTINCT a, b, c, d)
keys: a (type: int), b (type: int), c (type: int), d (type: int)
mode: hash
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23
- Statistics: Num rows: 7 Data size: 112 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 528 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int), _col3 (type: int)
sort order: ++++
- Statistics: Num rows: 7 Data size: 112 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 528 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col4 (type: bigint), _col5 (type: bigint), _col6 (type: bigint), _col7 (type: bigint), _col8 (type: bigint)
Execution mode: llap
LLAP IO: all inputs
@@ -200,14 +200,14 @@ STAGE PLANS:
aggregations: count(VALUE._col0), count(VALUE._col1), count(VALUE._col2), count(VALUE._col3), count(VALUE._col4), count(DISTINCT KEY._col0:0._col0), count(DISTINCT KEY._col0:1._col0), count(DISTINCT KEY._col0:2._col0), count(DISTINCT KEY._col0:3._col0), count(DISTINCT KEY._col0:4._col0, KEY._col0:4._col1), count(DISTINCT KEY._col0:5._col0, KEY._col0:5._col1), count(DISTINCT KEY._col0:6._col0, KEY._col0:6._col1), count(DISTINCT KEY._col0:7._col0, KEY._col0:7._col1), count(DISTINCT KEY._col0:8._col0, KEY._col0:8._col1), count(DISTINCT KEY._col0:9._col0, KEY._col0:9._col1), count(DISTINCT KEY._col0:10._col0, KEY._col0:10._col1, KEY._col0:10._col2), count(DISTINCT KEY._col0:11._col0, KEY._col0:11._col1, KEY._col0:11._col2), count(DISTINCT KEY._col0:12._col0, KEY._col0:12._col1, KEY._col0:12._col2), count(DISTINCT KEY._col0:13._col0, KEY._col0:13._col1, KEY._col0:13._col2), count(DISTINCT KEY._col0:14._col0, KEY._col0:14._col1, KEY._col0:14._col2, KEY._col0:14._col3)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19
- Statistics: Num rows: 1 Data size: 208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 160 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: bigint), _col0 (type: bigint), _col1 (type: bigint), _col2 (type: bigint), _col3 (type: bigint), _col4 (type: bigint), _col5 (type: bigint), _col6 (type: bigint), _col7 (type: bigint), _col8 (type: bigint), _col9 (type: bigint), _col10 (type: bigint), _col11 (type: bigint), _col12 (type: bigint), _col13 (type: bigint), _col14 (type: bigint), _col15 (type: bigint), _col16 (type: bigint), _col17 (type: bigint), _col18 (type: bigint), _col19 (type: bigint)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20
- Statistics: Num rows: 1 Data size: 208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 168 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 168 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -256,7 +256,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: abcd
- Statistics: Num rows: 7 Data size: 112 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 7 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Select Operator
@@ -266,7 +266,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1, 2, 3]
- Statistics: Num rows: 7 Data size: 112 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 7 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: a (type: int), b (type: int), c (type: int)
sort order: +++
@@ -276,7 +276,7 @@ STAGE PLANS:
native: false
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
nativeConditionsNotMet: No DISTINCT columns IS false
- Statistics: Num rows: 7 Data size: 112 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 7 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: d (type: int)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -302,10 +302,10 @@ STAGE PLANS:
keys: KEY._col0 (type: int)
mode: complete
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 3 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 3 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -357,7 +357,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: abcd
- Statistics: Num rows: 7 Data size: 112 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 7 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Select Operator
@@ -367,7 +367,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1, 2, 3]
- Statistics: Num rows: 7 Data size: 112 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 7 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: a (type: int), b (type: int), c (type: int), d (type: int)
sort order: ++++
@@ -376,7 +376,7 @@ STAGE PLANS:
native: false
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
nativeConditionsNotMet: No DISTINCT columns IS false
- Statistics: Num rows: 7 Data size: 112 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 7 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -400,14 +400,14 @@ STAGE PLANS:
aggregations: count(), count(KEY._col0:0._col0), count(KEY._col0:1._col0), count(KEY._col0:2._col0), count(KEY._col0:3._col0), count(DISTINCT KEY._col0:0._col0), count(DISTINCT KEY._col0:1._col0), count(DISTINCT KEY._col0:2._col0), count(DISTINCT KEY._col0:3._col0), count(DISTINCT KEY._col0:4._col0, KEY._col0:4._col1), count(DISTINCT KEY._col0:5._col0, KEY._col0:5._col1), count(DISTINCT KEY._col0:6._col0, KEY._col0:6._col1), count(DISTINCT KEY._col0:7._col0, KEY._col0:7._col1), count(DISTINCT KEY._col0:8._col0, KEY._col0:8._col1), count(DISTINCT KEY._col0:9._col0, KEY._col0:9._col1), count(DISTINCT KEY._col0:10._col0, KEY._col0:10._col1, KEY._col0:10._col2), count(DISTINCT KEY._col0:11._col0, KEY._col0:11._col1, KEY._col0:11._col2), count(DISTINCT KEY._col0:12._col0, KEY._col0:12._col1, KEY._col0:12._col2), count(DISTINCT KEY._col0:13._col0, KEY._col0:13._col1, KEY._col0:13._col2), count(DISTINCT KEY._col0:14._col0, KEY._col0:14._col1, KEY._col0:14._col2, KEY._col0:1
4._col3)
mode: complete
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19
- Statistics: Num rows: 1 Data size: 176 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 160 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: bigint), _col0 (type: bigint), _col1 (type: bigint), _col2 (type: bigint), _col3 (type: bigint), _col4 (type: bigint), _col5 (type: bigint), _col6 (type: bigint), _col7 (type: bigint), _col8 (type: bigint), _col9 (type: bigint), _col10 (type: bigint), _col11 (type: bigint), _col12 (type: bigint), _col13 (type: bigint), _col14 (type: bigint), _col15 (type: bigint), _col16 (type: bigint), _col17 (type: bigint), _col18 (type: bigint), _col19 (type: bigint)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20
- Statistics: Num rows: 1 Data size: 176 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 168 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 176 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 168 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/vector_decimal_10_0.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/vector_decimal_10_0.q.out b/ql/src/test/results/clientpositive/llap/vector_decimal_10_0.q.out
index 9f940d3..39fd39d 100644
--- a/ql/src/test/results/clientpositive/llap/vector_decimal_10_0.q.out
+++ b/ql/src/test/results/clientpositive/llap/vector_decimal_10_0.q.out
@@ -63,7 +63,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: decimal
- Statistics: Num rows: 2 Data size: 224 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:dec:decimal(10,0)/DECIMAL_64, 1:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -74,7 +74,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0]
- Statistics: Num rows: 2 Data size: 224 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: decimal(10,0))
sort order: +
@@ -83,7 +83,7 @@ STAGE PLANS:
keyColumns: 0:decimal(10,0)
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez 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: 2 Data size: 224 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -124,13 +124,13 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0]
- Statistics: Num rows: 2 Data size: 224 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 2 Data size: 224 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/vector_decimal_6.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/vector_decimal_6.q.out b/ql/src/test/results/clientpositive/llap/vector_decimal_6.q.out
index ef2d74c..ad1757c 100644
--- a/ql/src/test/results/clientpositive/llap/vector_decimal_6.q.out
+++ b/ql/src/test/results/clientpositive/llap/vector_decimal_6.q.out
@@ -652,7 +652,7 @@ PLAN VECTORIZATION:
STAGE DEPENDENCIES:
Stage-1 is a root stage
Stage-2 depends on stages: Stage-1
- Stage-4 depends on stages: Stage-2, Stage-0
+ Stage-4 depends on stages: Stage-0, Stage-2
Stage-3 depends on stages: Stage-4
Stage-0 depends on stages: Stage-1
@@ -710,40 +710,45 @@ STAGE PLANS:
partitionColumnCount: 0
scratchColumnTypeNames: [decimal(11,5)/DECIMAL_64, bigint]
Reducer 2
- Execution mode: vectorized, llap
+ Execution mode: llap
Reduce Vectorization:
enabled: true
enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true
- reduceColumnNullOrder: z
- reduceColumnSortOrder: +
- allNative: false
- usesVectorUDFAdaptor: false
- vectorized: true
- rowBatchContext:
- dataColumnCount: 2
- dataColumns: KEY.reducesinkkey0:int, VALUE._col0:decimal(11,5)
- partitionColumnCount: 0
- scratchColumnTypeNames: []
+ notVectorizedReason: Aggregation Function expression for GROUPBY operator: UDF compute_stats not supported
+ vectorized: false
Reduce Operator Tree:
Select Operator
expressions: VALUE._col0 (type: decimal(11,5)), KEY.reducesinkkey0 (type: int)
outputColumnNames: _col0, _col1
- Select Vectorization:
- className: VectorSelectOperator
- native: true
- projectedOutputColumnNums: [1, 0]
Statistics: Num rows: 27 Data size: 3132 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- File Sink Vectorization:
- className: VectorFileSinkOperator
- native: false
Statistics: Num rows: 27 Data size: 3132 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat
serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde
name: default.DECIMAL_6_3
+ Select Operator
+ expressions: _col0 (type: decimal(11,5)), _col1 (type: int)
+ outputColumnNames: col1, col2
+ Statistics: Num rows: 27 Data size: 3132 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: compute_stats(col1, 'hll'), compute_stats(col2, 'hll')
+ mode: complete
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 1056 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: _col0 (type: struct<columntype:string,min:decimal(11,5),max:decimal(11,5),countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 1056 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 1056 Basic stats: COMPLETE Column stats: COMPLETE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
Stage: Stage-2
Dependency Collection
@@ -760,6 +765,10 @@ STAGE PLANS:
Stage: Stage-3
Stats Work
Basic Stats Work:
+ Column Stats Desc:
+ Columns: k, v
+ Column Types: decimal(11,5), int
+ Table: default.DECIMAL_6_3
Stage: Stage-0
Move Operator