diff --git ql/src/java/org/apache/hadoop/hive/ql/exec/vector/expressions/CastStringToLong.java ql/src/java/org/apache/hadoop/hive/ql/exec/vector/expressions/CastStringToLong.java new file mode 100644 index 0000000..bde28e8 --- /dev/null +++ ql/src/java/org/apache/hadoop/hive/ql/exec/vector/expressions/CastStringToLong.java @@ -0,0 +1,270 @@ +/** + * Licensed to the Apache Software Foundation (ASF) under one + * or more contributor license agreements. See the NOTICE file + * distributed with this work for additional information + * regarding copyright ownership. The ASF licenses this file + * to you under the Apache License, Version 2.0 (the + * "License"); you may not use this file except in compliance + * with the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +package org.apache.hadoop.hive.ql.exec.vector.expressions; + +import org.apache.hadoop.hive.ql.exec.vector.BytesColumnVector; +import org.apache.hadoop.hive.ql.exec.vector.LongColumnVector; +import org.apache.hadoop.hive.ql.exec.vector.VectorExpressionDescriptor; +import org.apache.hadoop.hive.ql.exec.vector.VectorizedRowBatch; +import org.apache.hadoop.hive.serde2.lazy.LazyByte; +import org.apache.hadoop.hive.serde2.lazy.LazyInteger; +import org.apache.hadoop.hive.serde2.lazy.LazyLong; +import org.apache.hadoop.hive.serde2.lazy.LazyShort; +import org.apache.hadoop.hive.serde2.lazy.LazyUtils; +import org.apache.hadoop.hive.serde2.objectinspector.PrimitiveObjectInspector.PrimitiveCategory; +import org.apache.hadoop.hive.serde2.typeinfo.PrimitiveTypeInfo; +import org.apache.hadoop.hive.serde2.typeinfo.TypeInfo; +import org.apache.hadoop.hive.serde2.typeinfo.TypeInfoUtils; + +/** + * Cast a string to a long. + * + * If other functions besides cast need to take a string in and produce a long, + * you can subclass this class or convert it to a superclass, and + * implement different "func()" methods for each operation. + */ +public class CastStringToLong extends VectorExpression { + private static final long serialVersionUID = 1L; + int inputColumn; + int outputColumn; + + private transient boolean integerPrimitiveCategoryKnown = false; + protected transient PrimitiveCategory integerPrimitiveCategory; + + public CastStringToLong(int inputColumn, int outputColumn) { + this.inputColumn = inputColumn; + this.outputColumn = outputColumn; + } + + public CastStringToLong() { + super(); + } + + /** + * Convert input string to a long, at position i in the respective vectors. + */ + protected void func(LongColumnVector outV, BytesColumnVector inV, int batchIndex) { + + byte[] bytes = inV.vector[batchIndex]; + final int start = inV.start[batchIndex]; + final int length = inV.length[batchIndex]; + try { + + switch (integerPrimitiveCategory) { + case BOOLEAN: + { + boolean booleanValue; + int i = start; + if (length == 4) { + if ((bytes[i] == 'T' || bytes[i] == 't') && + (bytes[i + 1] == 'R' || bytes[i + 1] == 'r') && + (bytes[i + 2] == 'U' || bytes[i + 2] == 'u') && + (bytes[i + 3] == 'E' || bytes[i + 3] == 'e')) { + booleanValue = true; + } else { + // No boolean value match for 4 char field. + outV.noNulls = false; + outV.isNull[batchIndex] = true; + return; + } + } else if (length == 5) { + if ((bytes[i] == 'F' || bytes[i] == 'f') && + (bytes[i + 1] == 'A' || bytes[i + 1] == 'a') && + (bytes[i + 2] == 'L' || bytes[i + 2] == 'l') && + (bytes[i + 3] == 'S' || bytes[i + 3] == 's') && + (bytes[i + 4] == 'E' || bytes[i + 4] == 'e')) { + booleanValue = false; + } else { + // No boolean value match for 5 char field. + outV.noNulls = false; + outV.isNull[batchIndex] = true; + return; + } + } else if (length == 1) { + byte b = bytes[start]; + if (b == '1' || b == 't' || b == 'T') { + booleanValue = true; + } else if (b == '0' || b == 'f' || b == 'F') { + booleanValue = false; + } else { + // No boolean value match for extended 1 char field. + outV.noNulls = false; + outV.isNull[batchIndex] = true; + return; + } + } else { + // No boolean value match for other lengths. + outV.noNulls = false; + outV.isNull[batchIndex] = true; + return; + } + outV.vector[batchIndex] = (booleanValue ? 1 : 0); + } + break; + case BYTE: + if (!LazyUtils.isNumberMaybe(bytes, start, length)) { + outV.noNulls = false; + outV.isNull[batchIndex] = true; + return; + } + outV.vector[batchIndex] = LazyByte.parseByte(bytes, start, length, 10); + break; + case SHORT: + if (!LazyUtils.isNumberMaybe(bytes, start, length)) { + outV.noNulls = false; + outV.isNull[batchIndex] = true; + return; + } + outV.vector[batchIndex] = LazyShort.parseShort(bytes, start, length, 10); + break; + case INT: + if (!LazyUtils.isNumberMaybe(bytes, start, length)) { + outV.noNulls = false; + outV.isNull[batchIndex] = true; + return; + } + outV.vector[batchIndex] = LazyInteger.parseInt(bytes, start, length, 10); + break; + case LONG: + if (!LazyUtils.isNumberMaybe(bytes, start, length)) { + outV.noNulls = false; + outV.isNull[batchIndex] = true; + return; + } + outV.vector[batchIndex] = LazyLong.parseLong(bytes, start, length, 10); + break; + default: + throw new Error("Unexpected primitive category " + integerPrimitiveCategory); + } + } catch (Exception e) { + + // for any exception in conversion to integer, produce NULL + outV.noNulls = false; + outV.isNull[batchIndex] = true; + } + } + + @Override + public void evaluate(VectorizedRowBatch batch) { + + if (!integerPrimitiveCategoryKnown) { + String typeName = getOutputType().toLowerCase(); + TypeInfo typeInfo = TypeInfoUtils.getTypeInfoFromTypeString(typeName); + integerPrimitiveCategory = ((PrimitiveTypeInfo) typeInfo).getPrimitiveCategory(); + integerPrimitiveCategoryKnown = true; + } + + if (childExpressions != null) { + super.evaluateChildren(batch); + } + + BytesColumnVector inV = (BytesColumnVector) batch.cols[inputColumn]; + int[] sel = batch.selected; + int n = batch.size; + LongColumnVector outV = (LongColumnVector) batch.cols[outputColumn]; + + if (n == 0) { + + // Nothing to do + return; + } + + if (inV.noNulls) { + outV.noNulls = true; + if (inV.isRepeating) { + outV.isRepeating = true; + func(outV, inV, 0); + } else if (batch.selectedInUse) { + for(int j = 0; j != n; j++) { + int i = sel[j]; + func(outV, inV, i); + } + outV.isRepeating = false; + } else { + for(int i = 0; i != n; i++) { + func(outV, inV, i); + } + outV.isRepeating = false; + } + } else { + + // Handle case with nulls. Don't do function if the value is null, + // because the data may be undefined for a null value. + outV.noNulls = false; + if (inV.isRepeating) { + outV.isRepeating = true; + outV.isNull[0] = inV.isNull[0]; + if (!inV.isNull[0]) { + func(outV, inV, 0); + } + } else if (batch.selectedInUse) { + for(int j = 0; j != n; j++) { + int i = sel[j]; + outV.isNull[i] = inV.isNull[i]; + if (!inV.isNull[i]) { + func(outV, inV, i); + } + } + outV.isRepeating = false; + } else { + System.arraycopy(inV.isNull, 0, outV.isNull, 0, n); + for(int i = 0; i != n; i++) { + if (!inV.isNull[i]) { + func(outV, inV, i); + } + } + outV.isRepeating = false; + } + } + } + + @Override + public int getOutputColumn() { + return outputColumn; + } + + public void setOutputColumn(int outputColumn) { + this.outputColumn = outputColumn; + } + + public int getInputColumn() { + return inputColumn; + } + + public void setInputColumn(int inputColumn) { + this.inputColumn = inputColumn; + } + + @Override + public String vectorExpressionParameters() { + return "col " + inputColumn; + } + + @Override + public VectorExpressionDescriptor.Descriptor getDescriptor() { + VectorExpressionDescriptor.Builder b = new VectorExpressionDescriptor.Builder(); + b.setMode(VectorExpressionDescriptor.Mode.PROJECTION) + .setNumArguments(1) + .setArgumentTypes( + VectorExpressionDescriptor.ArgumentType.STRING_FAMILY) + .setInputExpressionTypes( + VectorExpressionDescriptor.InputExpressionType.COLUMN); + return b.build(); + } +} \ No newline at end of file diff --git ql/src/java/org/apache/hadoop/hive/ql/udf/UDFToBoolean.java ql/src/java/org/apache/hadoop/hive/ql/udf/UDFToBoolean.java index 0cc0c9e..7cdf2c3 100755 --- ql/src/java/org/apache/hadoop/hive/ql/udf/UDFToBoolean.java +++ ql/src/java/org/apache/hadoop/hive/ql/udf/UDFToBoolean.java @@ -23,6 +23,7 @@ import org.apache.hadoop.hive.ql.exec.UDF; import org.apache.hadoop.hive.ql.exec.vector.VectorizedExpressions; import org.apache.hadoop.hive.ql.exec.vector.expressions.CastDecimalToBoolean; +import org.apache.hadoop.hive.ql.exec.vector.expressions.CastStringToLong; import org.apache.hadoop.hive.ql.exec.vector.expressions.gen.CastDoubleToBooleanViaDoubleToLong; import org.apache.hadoop.hive.ql.exec.vector.expressions.gen.CastLongToBooleanViaLongToLong; import org.apache.hadoop.hive.ql.exec.vector.expressions.gen.CastDateToBooleanViaLongToLong; @@ -46,7 +47,7 @@ */ @VectorizedExpressions({CastLongToBooleanViaLongToLong.class, CastDateToBooleanViaLongToLong.class, CastTimestampToBoolean.class, - CastDoubleToBooleanViaDoubleToLong.class, CastDecimalToBoolean.class}) + CastDoubleToBooleanViaDoubleToLong.class, CastDecimalToBoolean.class, CastStringToLong.class}) public class UDFToBoolean extends UDF { private final BooleanWritable booleanWritable = new BooleanWritable(); diff --git ql/src/java/org/apache/hadoop/hive/ql/udf/UDFToByte.java ql/src/java/org/apache/hadoop/hive/ql/udf/UDFToByte.java index df2b42f..12f530b 100755 --- ql/src/java/org/apache/hadoop/hive/ql/udf/UDFToByte.java +++ ql/src/java/org/apache/hadoop/hive/ql/udf/UDFToByte.java @@ -21,6 +21,7 @@ import org.apache.hadoop.hive.ql.exec.UDF; import org.apache.hadoop.hive.ql.exec.vector.VectorizedExpressions; import org.apache.hadoop.hive.ql.exec.vector.expressions.CastDecimalToLong; +import org.apache.hadoop.hive.ql.exec.vector.expressions.CastStringToLong; import org.apache.hadoop.hive.ql.exec.vector.expressions.gen.CastDoubleToLong; import org.apache.hadoop.hive.ql.exec.vector.expressions.CastTimestampToLong; import org.apache.hadoop.hive.serde2.io.ByteWritable; @@ -42,7 +43,7 @@ * */ @VectorizedExpressions({CastTimestampToLong.class, CastDoubleToLong.class, - CastDecimalToLong.class}) + CastDecimalToLong.class, CastStringToLong.class}) public class UDFToByte extends UDF { private final ByteWritable byteWritable = new ByteWritable(); diff --git ql/src/java/org/apache/hadoop/hive/ql/udf/UDFToInteger.java ql/src/java/org/apache/hadoop/hive/ql/udf/UDFToInteger.java index 42972c7..461ef86 100755 --- ql/src/java/org/apache/hadoop/hive/ql/udf/UDFToInteger.java +++ ql/src/java/org/apache/hadoop/hive/ql/udf/UDFToInteger.java @@ -22,6 +22,7 @@ import org.apache.hadoop.hive.ql.exec.vector.VectorizedExpressions; import org.apache.hadoop.hive.ql.exec.vector.expressions.CastDecimalToLong; import org.apache.hadoop.hive.ql.exec.vector.expressions.gen.CastDoubleToLong; +import org.apache.hadoop.hive.ql.exec.vector.expressions.CastStringToLong; import org.apache.hadoop.hive.ql.exec.vector.expressions.CastTimestampToLong; import org.apache.hadoop.hive.ql.io.RecordIdentifier; import org.apache.hadoop.hive.serde2.io.ByteWritable; @@ -43,7 +44,7 @@ * */ @VectorizedExpressions({CastTimestampToLong.class, CastDoubleToLong.class, - CastDecimalToLong.class}) + CastDecimalToLong.class, CastStringToLong.class}) public class UDFToInteger extends UDF { private final IntWritable intWritable = new IntWritable(); diff --git ql/src/java/org/apache/hadoop/hive/ql/udf/UDFToLong.java ql/src/java/org/apache/hadoop/hive/ql/udf/UDFToLong.java index 847b535..11f6a6c 100755 --- ql/src/java/org/apache/hadoop/hive/ql/udf/UDFToLong.java +++ ql/src/java/org/apache/hadoop/hive/ql/udf/UDFToLong.java @@ -21,6 +21,7 @@ import org.apache.hadoop.hive.ql.exec.UDF; import org.apache.hadoop.hive.ql.exec.vector.VectorizedExpressions; import org.apache.hadoop.hive.ql.exec.vector.expressions.CastDecimalToLong; +import org.apache.hadoop.hive.ql.exec.vector.expressions.CastStringToLong; import org.apache.hadoop.hive.ql.exec.vector.expressions.gen.CastDoubleToLong; import org.apache.hadoop.hive.ql.exec.vector.expressions.CastTimestampToLong; import org.apache.hadoop.hive.serde2.io.ByteWritable; @@ -42,7 +43,7 @@ * */ @VectorizedExpressions({CastTimestampToLong.class, CastDoubleToLong.class, - CastDecimalToLong.class}) + CastDecimalToLong.class, CastStringToLong.class}) public class UDFToLong extends UDF { private final LongWritable longWritable = new LongWritable(); diff --git ql/src/java/org/apache/hadoop/hive/ql/udf/UDFToShort.java ql/src/java/org/apache/hadoop/hive/ql/udf/UDFToShort.java index 0ae0c13..5372549 100644 --- ql/src/java/org/apache/hadoop/hive/ql/udf/UDFToShort.java +++ ql/src/java/org/apache/hadoop/hive/ql/udf/UDFToShort.java @@ -22,6 +22,7 @@ import org.apache.hadoop.hive.ql.exec.vector.VectorizedExpressions; import org.apache.hadoop.hive.ql.exec.vector.expressions.CastDecimalToDouble; import org.apache.hadoop.hive.ql.exec.vector.expressions.CastDecimalToLong; +import org.apache.hadoop.hive.ql.exec.vector.expressions.CastStringToLong; import org.apache.hadoop.hive.ql.exec.vector.expressions.gen.CastDoubleToLong; import org.apache.hadoop.hive.ql.exec.vector.expressions.CastTimestampToLong; import org.apache.hadoop.hive.serde2.io.ByteWritable; @@ -43,7 +44,7 @@ * */ @VectorizedExpressions({CastTimestampToLong.class, CastDoubleToLong.class, - CastDecimalToLong.class}) + CastDecimalToLong.class, CastStringToLong.class}) public class UDFToShort extends UDF { ShortWritable shortWritable = new ShortWritable(); diff --git ql/src/test/queries/clientpositive/schema_evol_orc_acid_part.q ql/src/test/queries/clientpositive/schema_evol_orc_acid_part.q index 25ec8bb..09d7050 100644 --- ql/src/test/queries/clientpositive/schema_evol_orc_acid_part.q +++ ql/src/test/queries/clientpositive/schema_evol_orc_acid_part.q @@ -1,3 +1,5 @@ +set hive.explain.user=false; +set hive.fetch.task.conversion=none; set hive.mapred.mode=nonstrict; set hive.cli.print.header=true; set hive.support.concurrency=true; @@ -7,7 +9,6 @@ SET hive.exec.schema.evolution=false; SET hive.vectorized.use.vectorized.input.format=true; SET hive.vectorized.use.vector.serde.deserialize=false; SET hive.vectorized.use.row.serde.deserialize=false; -set hive.fetch.task.conversion=none; SET hive.vectorized.execution.enabled=false; set hive.exec.dynamic.partition.mode=nonstrict; set hive.metastore.disallow.incompatible.col.type.changes=true; @@ -18,7 +19,8 @@ set hive.llap.io.enabled=false; -- -- FILE VARIATION: ORC, ACID Non-Vectorized, MapWork, Partitioned -- *IMPORTANT NOTE* We set hive.exec.schema.evolution=false above since schema evolution is always used for ACID. --- Also, we don't do EXPLAINs on ACID files because the transaction id causes Q file statistics differences... +-- Also, we don't do regular EXPLAINs on ACID files because the transaction id causes Q file statistics differences... +-- Instead just one explain vectorization only detail -- CREATE TABLE schema_evolution_data(insert_num int, boolean1 boolean, tinyint1 tinyint, smallint1 smallint, int1 int, bigint1 bigint, decimal1 decimal(38,18), float1 float, double1 double, string1 string, string2 string, date1 date, timestamp1 timestamp, boolean_str string, tinyint_str string, smallint_str string, int_str string, bigint_str string, decimal_str string, float_str string, double_str string, date_str string, timestamp_str string, filler string) @@ -61,6 +63,9 @@ alter table part_add_int_string_permute_select add columns(c int, d string); insert into table part_add_int_string_permute_select partition(part=1) VALUES (2, 2222, 'new', 3333, '4444'); +explain vectorization only detail +select insert_num,part,a,b,c,d from part_add_int_string_permute_select; + -- SELECT permutation columns to make sure NULL defaulting works right select insert_num,part,a,b from part_add_int_string_permute_select; select insert_num,part,a,b,c from part_add_int_string_permute_select; @@ -155,9 +160,6 @@ insert into table part_change_numeric_group_string_group_multi_ints_string_group 'filler', 'filler', 'filler', 'filler', 'filler', 'filler', 'filler', 'filler', 'new'); -explain -select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,c16,c17,c18,c19,c20,b from part_change_numeric_group_string_group_multi_ints_string_group; - select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,c16,c17,c18,c19,c20,b from part_change_numeric_group_string_group_multi_ints_string_group; drop table part_change_numeric_group_string_group_multi_ints_string_group; @@ -198,9 +200,6 @@ insert into table part_change_numeric_group_string_group_floating_string_group p 'filler', 'filler', 'filler', 'filler', 'filler', 'filler', 'new'); -explain -select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,b from part_change_numeric_group_string_group_floating_string_group; - select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,b from part_change_numeric_group_string_group_floating_string_group; drop table part_change_numeric_group_string_group_floating_string_group; diff --git ql/src/test/queries/clientpositive/schema_evol_orc_acid_part_update.q ql/src/test/queries/clientpositive/schema_evol_orc_acid_part_update.q index e62d21c..17d461c 100644 --- ql/src/test/queries/clientpositive/schema_evol_orc_acid_part_update.q +++ ql/src/test/queries/clientpositive/schema_evol_orc_acid_part_update.q @@ -1,3 +1,5 @@ +set hive.explain.user=false; +set hive.fetch.task.conversion=none; set hive.mapred.mode=nonstrict; set hive.cli.print.header=true; set hive.support.concurrency=true; @@ -7,7 +9,6 @@ SET hive.exec.schema.evolution=false; SET hive.vectorized.use.vectorized.input.format=true; SET hive.vectorized.use.vector.serde.deserialize=false; SET hive.vectorized.use.row.serde.deserialize=false; -set hive.fetch.task.conversion=none; SET hive.vectorized.execution.enabled=false; set hive.exec.dynamic.partition.mode=nonstrict; set hive.metastore.disallow.incompatible.col.type.changes=true; diff --git ql/src/test/queries/clientpositive/schema_evol_orc_acid_table.q ql/src/test/queries/clientpositive/schema_evol_orc_acid_table.q index 7767d80..23af572 100644 --- ql/src/test/queries/clientpositive/schema_evol_orc_acid_table.q +++ ql/src/test/queries/clientpositive/schema_evol_orc_acid_table.q @@ -1,3 +1,5 @@ +set hive.explain.user=false; +set hive.fetch.task.conversion=none; set hive.cli.print.header=true; set hive.support.concurrency=true; set hive.txn.manager=org.apache.hadoop.hive.ql.lockmgr.DbTxnManager; @@ -6,7 +8,6 @@ SET hive.exec.schema.evolution=false; SET hive.vectorized.use.vectorized.input.format=true; SET hive.vectorized.use.vector.serde.deserialize=false; SET hive.vectorized.use.row.serde.deserialize=false; -set hive.fetch.task.conversion=none; SET hive.vectorized.execution.enabled=false; set hive.exec.dynamic.partition.mode=nonstrict; set hive.metastore.disallow.incompatible.col.type.changes=true; @@ -17,7 +18,8 @@ set hive.llap.io.enabled=false; -- -- FILE VARIATION: ORC, ACID Non-Vectorized, MapWork, Table -- *IMPORTANT NOTE* We set hive.exec.schema.evolution=false above since schema evolution is always used for ACID. --- Also, we don't do EXPLAINs on ACID files because the transaction id causes Q file statistics differences... +-- Also, we don't do regular EXPLAINs on ACID files because the transaction id causes Q file statistics differences... +-- Instead just one explain vectorization only detail -- CREATE TABLE schema_evolution_data(insert_num int, boolean1 boolean, tinyint1 tinyint, smallint1 smallint, int1 int, bigint1 bigint, decimal1 decimal(38,18), float1 float, double1 double, string1 string, string2 string, date1 date, timestamp1 timestamp, boolean_str string, tinyint_str string, smallint_str string, int_str string, bigint_str string, decimal_str string, float_str string, double_str string, date_str string, timestamp_str string, filler string) @@ -40,6 +42,9 @@ alter table table_add_int_permute_select add columns(c int); insert into table table_add_int_permute_select VALUES (111, 80000, 'new', 80000); +explain vectorization only detail +select insert_num,a,b,c from table_add_int_permute_select; + -- SELECT permutation columns to make sure NULL defaulting works right select insert_num,a,b from table_add_int_permute_select; select insert_num,a,b,c from table_add_int_permute_select; diff --git ql/src/test/queries/clientpositive/schema_evol_orc_acid_table_update.q ql/src/test/queries/clientpositive/schema_evol_orc_acid_table_update.q index 92a8699..4699cca 100644 --- ql/src/test/queries/clientpositive/schema_evol_orc_acid_table_update.q +++ ql/src/test/queries/clientpositive/schema_evol_orc_acid_table_update.q @@ -1,3 +1,5 @@ +set hive.explain.user=false; +set hive.fetch.task.conversion=none; set hive.cli.print.header=true; set hive.support.concurrency=true; set hive.txn.manager=org.apache.hadoop.hive.ql.lockmgr.DbTxnManager; @@ -6,7 +8,6 @@ SET hive.exec.schema.evolution=false; SET hive.vectorized.use.vectorized.input.format=true; SET hive.vectorized.use.vector.serde.deserialize=false; SET hive.vectorized.use.row.serde.deserialize=false; -set hive.fetch.task.conversion=none; SET hive.vectorized.execution.enabled=false; set hive.exec.dynamic.partition.mode=nonstrict; set hive.metastore.disallow.incompatible.col.type.changes=true; diff --git ql/src/test/queries/clientpositive/schema_evol_orc_acidvec_part.q ql/src/test/queries/clientpositive/schema_evol_orc_acidvec_part.q index fa6b741..1ad8650 100644 --- ql/src/test/queries/clientpositive/schema_evol_orc_acidvec_part.q +++ ql/src/test/queries/clientpositive/schema_evol_orc_acidvec_part.q @@ -1,3 +1,5 @@ +set hive.explain.user=false; +set hive.fetch.task.conversion=none; set hive.mapred.mode=nonstrict; set hive.cli.print.header=true; set hive.support.concurrency=true; @@ -7,7 +9,6 @@ SET hive.exec.schema.evolution=false; SET hive.vectorized.use.vectorized.input.format=true; SET hive.vectorized.use.vector.serde.deserialize=false; SET hive.vectorized.use.row.serde.deserialize=false; -set hive.fetch.task.conversion=none; SET hive.vectorized.execution.enabled=true; set hive.exec.dynamic.partition.mode=nonstrict; set hive.metastore.disallow.incompatible.col.type.changes=true; @@ -18,7 +19,8 @@ set hive.llap.io.enabled=false; -- -- FILE VARIATION: ORC, ACID Vectorized, MapWork, Partitioned -- *IMPORTANT NOTE* We set hive.exec.schema.evolution=false above since schema evolution is always used for ACID. --- Also, we don't do EXPLAINs on ACID files because the transaction id causes Q file statistics differences... +-- Also, we don't do regular EXPLAINs on ACID files because the transaction id causes Q file statistics differences... +-- Instead explain vectorization only detail -- CREATE TABLE schema_evolution_data(insert_num int, boolean1 boolean, tinyint1 tinyint, smallint1 smallint, int1 int, bigint1 bigint, decimal1 decimal(38,18), float1 float, double1 double, string1 string, string2 string, date1 date, timestamp1 timestamp, boolean_str string, tinyint_str string, smallint_str string, int_str string, bigint_str string, decimal_str string, float_str string, double_str string, date_str string, timestamp_str string, filler string) @@ -41,6 +43,9 @@ alter table part_add_int_permute_select add columns(c int); insert into table part_add_int_permute_select partition(part=1) VALUES (2, 2222, 'new', 3333); +explain vectorization only detail +select insert_num,part,a,b,c from part_add_int_permute_select; + -- SELECT permutation columns to make sure NULL defaulting works right select insert_num,part,a,b from part_add_int_permute_select; select insert_num,part,a,b,c from part_add_int_permute_select; @@ -61,6 +66,9 @@ alter table part_add_int_string_permute_select add columns(c int, d string); insert into table part_add_int_string_permute_select partition(part=1) VALUES (2, 2222, 'new', 3333, '4444'); +explain vectorization only detail +select insert_num,part,a,b,c,d from part_add_int_string_permute_select; + -- SELECT permutation columns to make sure NULL defaulting works right select insert_num,part,a,b from part_add_int_string_permute_select; select insert_num,part,a,b,c from part_add_int_string_permute_select; @@ -90,6 +98,9 @@ alter table part_change_string_group_double replace columns (insert_num int, c1 insert into table part_change_string_group_double partition(part=1) SELECT insert_num, double1, double1, double1, 'new' FROM schema_evolution_data WHERE insert_num = 111; +explain vectorization only detail +select insert_num,part,c1,c2,c3,b from part_change_string_group_double; + select insert_num,part,c1,c2,c3,b from part_change_string_group_double; drop table part_change_string_group_double; @@ -110,6 +121,9 @@ alter table part_change_date_group_string_group_date_timestamp replace columns(i insert into table part_change_date_group_string_group_date_timestamp partition(part=1) VALUES (111, 'filler', 'filler', 'filler', 'filler', 'filler', 'filler', 'filler', 'filler', 'filler', 'filler', 'new'); +explain vectorization only detail +select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,b from part_change_date_group_string_group_date_timestamp; + select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,b from part_change_date_group_string_group_date_timestamp; drop table part_change_date_group_string_group_date_timestamp; @@ -140,6 +154,9 @@ insert into table part_change_numeric_group_string_group_multi_ints_string_group tinyint1, smallint1, int1, bigint1, tinyint1, smallint1, int1, bigint1, 'original' FROM schema_evolution_data; +explain vectorization only detail +select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,c16,c17,c18,c19,c20,b from part_change_numeric_group_string_group_multi_ints_string_group; + select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,c16,c17,c18,c19,c20,b from part_change_numeric_group_string_group_multi_ints_string_group; -- Table-Non-Cascade CHANGE COLUMNS ... @@ -155,7 +172,7 @@ insert into table part_change_numeric_group_string_group_multi_ints_string_group 'filler', 'filler', 'filler', 'filler', 'filler', 'filler', 'filler', 'filler', 'new'); -explain +explain vectorization only detail select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,c16,c17,c18,c19,c20,b from part_change_numeric_group_string_group_multi_ints_string_group; select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,c16,c17,c18,c19,c20,b from part_change_numeric_group_string_group_multi_ints_string_group; @@ -183,6 +200,9 @@ insert into table part_change_numeric_group_string_group_floating_string_group p decimal1, float1, double1, decimal1, float1, double1, 'original' FROM schema_evolution_data; +explain vectorization only detail +select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,b from part_change_numeric_group_string_group_floating_string_group; + select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,b from part_change_numeric_group_string_group_floating_string_group; -- Table-Non-Cascade CHANGE COLUMNS ... @@ -198,7 +218,7 @@ insert into table part_change_numeric_group_string_group_floating_string_group p 'filler', 'filler', 'filler', 'filler', 'filler', 'filler', 'new'); -explain +explain vectorization only detail select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,b from part_change_numeric_group_string_group_floating_string_group; select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,b from part_change_numeric_group_string_group_floating_string_group; @@ -226,6 +246,9 @@ insert into table part_change_string_group_string_group_string partition(part=1) string2, string2, string2, 'original' FROM schema_evolution_data; +explain vectorization only detail +select insert_num,part,c1,c2,c3,c4,b from part_change_string_group_string_group_string; + select insert_num,part,c1,c2,c3,c4,b from part_change_string_group_string_group_string; -- Table-Non-Cascade CHANGE COLUMNS ... @@ -240,6 +263,9 @@ insert into table part_change_string_group_string_group_string partition(part=1) 'filler', 'filler', 'filler', 'new'); +explain vectorization only detail +select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,b from part_change_string_group_string_group_string; + select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,b from part_change_string_group_string_group_string; drop table part_change_string_group_string_group_string; @@ -270,6 +296,9 @@ insert into table part_change_lower_to_higher_numeric_group_tinyint_to_bigint pa bigint1, bigint1, bigint1, 'original' FROM schema_evolution_data; +explain vectorization only detail +select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,c16,c17,c18,b from part_change_lower_to_higher_numeric_group_tinyint_to_bigint; + select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,c16,c17,c18,b from part_change_lower_to_higher_numeric_group_tinyint_to_bigint; -- Table-Non-Cascade CHANGE COLUMNS ... @@ -287,6 +316,9 @@ insert into table part_change_lower_to_higher_numeric_group_tinyint_to_bigint pa 1234.5678, 9876.543, 789.321, 'new'); +explain vectorization only detail +select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,c16,c17,c18,b from part_change_lower_to_higher_numeric_group_tinyint_to_bigint; + select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,c16,c17,c18,b from part_change_lower_to_higher_numeric_group_tinyint_to_bigint; drop table part_change_lower_to_higher_numeric_group_tinyint_to_bigint; @@ -308,6 +340,9 @@ insert into table part_change_lower_to_higher_numeric_group_decimal_to_float par float1, 'original' FROM schema_evolution_data; +explain vectorization only detail +select insert_num,part,c1,c2,c3,b from part_change_lower_to_higher_numeric_group_decimal_to_float; + select insert_num,part,c1,c2,c3,b from part_change_lower_to_higher_numeric_group_decimal_to_float; -- Table-Non-Cascade CHANGE COLUMNS ... @@ -315,6 +350,9 @@ alter table part_change_lower_to_higher_numeric_group_decimal_to_float replace c insert into table part_change_lower_to_higher_numeric_group_decimal_to_float partition(part=1) VALUES (111, 1234.5678, 9876.543, 1234.5678, 'new'); +explain vectorization only detail +select insert_num,part,c1,c2,c3,b from part_change_lower_to_higher_numeric_group_decimal_to_float; + select insert_num,part,c1,c2,c3,b from part_change_lower_to_higher_numeric_group_decimal_to_float; drop table part_change_lower_to_higher_numeric_group_decimal_to_float; \ No newline at end of file diff --git ql/src/test/queries/clientpositive/schema_evol_orc_acidvec_part_update.q ql/src/test/queries/clientpositive/schema_evol_orc_acidvec_part_update.q index c77af86..9a6bcaa 100644 --- ql/src/test/queries/clientpositive/schema_evol_orc_acidvec_part_update.q +++ ql/src/test/queries/clientpositive/schema_evol_orc_acidvec_part_update.q @@ -1,3 +1,5 @@ +set hive.explain.user=false; +set hive.fetch.task.conversion=none; set hive.mapred.mode=nonstrict; set hive.cli.print.header=true; set hive.support.concurrency=true; @@ -7,7 +9,6 @@ SET hive.exec.schema.evolution=false; SET hive.vectorized.use.vectorized.input.format=true; SET hive.vectorized.use.vector.serde.deserialize=false; SET hive.vectorized.use.row.serde.deserialize=false; -set hive.fetch.task.conversion=none; SET hive.vectorized.execution.enabled=true; set hive.exec.dynamic.partition.mode=nonstrict; set hive.metastore.disallow.incompatible.col.type.changes=true; diff --git ql/src/test/queries/clientpositive/schema_evol_orc_acidvec_table.q ql/src/test/queries/clientpositive/schema_evol_orc_acidvec_table.q index 1dab162..7e23d7f 100644 --- ql/src/test/queries/clientpositive/schema_evol_orc_acidvec_table.q +++ ql/src/test/queries/clientpositive/schema_evol_orc_acidvec_table.q @@ -1,3 +1,5 @@ +set hive.explain.user=false; +set hive.fetch.task.conversion=none; set hive.cli.print.header=true; set hive.support.concurrency=true; set hive.txn.manager=org.apache.hadoop.hive.ql.lockmgr.DbTxnManager; @@ -6,7 +8,6 @@ SET hive.exec.schema.evolution=false; SET hive.vectorized.use.vectorized.input.format=true; SET hive.vectorized.use.vector.serde.deserialize=false; SET hive.vectorized.use.row.serde.deserialize=false; -set hive.fetch.task.conversion=none; SET hive.vectorized.execution.enabled=true; set hive.exec.dynamic.partition.mode=nonstrict; set hive.metastore.disallow.incompatible.col.type.changes=true; @@ -17,7 +18,8 @@ set hive.llap.io.enabled=false; -- -- FILE VARIATION: ORC, ACID Vectorized, MapWork, Table -- *IMPORTANT NOTE* We set hive.exec.schema.evolution=false above since schema evolution is always used for ACID. --- Also, we don't do EXPLAINs on ACID files because the transaction id causes Q file statistics differences... +-- Also, we don't do regular EXPLAINs on ACID files because the transaction id causes Q file statistics differences... +-- Instead explain vectorization only detail -- CREATE TABLE schema_evolution_data(insert_num int, boolean1 boolean, tinyint1 tinyint, smallint1 smallint, int1 int, bigint1 bigint, decimal1 decimal(38,18), float1 float, double1 double, string1 string, string2 string, date1 date, timestamp1 timestamp, boolean_str string, tinyint_str string, smallint_str string, int_str string, bigint_str string, decimal_str string, float_str string, double_str string, date_str string, timestamp_str string, filler string) @@ -40,6 +42,9 @@ alter table table_add_int_permute_select add columns(c int); insert into table table_add_int_permute_select VALUES (111, 80000, 'new', 80000); +explain vectorization only detail +select insert_num,a,b,c from table_add_int_permute_select; + -- SELECT permutation columns to make sure NULL defaulting works right select insert_num,a,b from table_add_int_permute_select; select insert_num,a,b,c from table_add_int_permute_select; @@ -60,6 +65,9 @@ alter table table_add_int_string_permute_select add columns(c int, d string); insert into table table_add_int_string_permute_select VALUES (111, 80000, 'new', 80000, 'filler'); +explain vectorization only detail +select insert_num,a,b,c,d from table_add_int_string_permute_select; + -- SELECT permutation columns to make sure NULL defaulting works right select insert_num,a,b from table_add_int_string_permute_select; select insert_num,a,b,c from table_add_int_string_permute_select; @@ -89,6 +97,9 @@ alter table table_change_string_group_double replace columns (insert_num int, c1 insert into table table_change_string_group_double VALUES (111, 789.321, 789.321, 789.321, 'new'); +explain vectorization only detail +select insert_num,c1,c2,c3,b from table_change_string_group_double; + select insert_num,c1,c2,c3,b from table_change_string_group_double; drop table table_change_string_group_double; @@ -109,6 +120,9 @@ alter table table_change_date_group_string_group_date_group replace columns(inse insert into table table_change_date_group_string_group_date_group VALUES (111, 'filler', 'filler', 'filler', 'filler', 'filler', 'filler', 'filler', 'filler', 'filler', 'filler', 'new'); +explain vectorization only detail +select insert_num,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,b from table_change_date_group_string_group_date_group; + select insert_num,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,b from table_change_date_group_string_group_date_group; drop table table_change_date_group_string_group_date_group; @@ -138,6 +152,9 @@ insert into table table_change_numeric_group_string_group_multi_ints_string_grou tinyint1, smallint1, int1, bigint1, tinyint1, smallint1, int1, bigint1, 'original' FROM schema_evolution_data; +explain vectorization only detail +select insert_num,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,c16,c17,c18,c19,c20,b from table_change_numeric_group_string_group_multi_ints_string_group; + select insert_num,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,c16,c17,c18,c19,c20,b from table_change_numeric_group_string_group_multi_ints_string_group; -- Table-Non-Cascade CHANGE COLUMNS ... @@ -153,6 +170,9 @@ insert into table table_change_numeric_group_string_group_multi_ints_string_grou 'filler', 'filler', 'filler', 'filler', 'filler', 'filler', 'filler', 'filler', 'new'); +explain vectorization only detail +select insert_num,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,c16,c17,c18,c19,c20,b from table_change_numeric_group_string_group_multi_ints_string_group; + select insert_num,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,c16,c17,c18,c19,c20,b from table_change_numeric_group_string_group_multi_ints_string_group; drop table table_change_numeric_group_string_group_multi_ints_string_group; @@ -178,6 +198,9 @@ insert into table table_change_numeric_group_string_group_floating_string_group decimal1, float1, double1, decimal1, float1, double1, 'original' FROM schema_evolution_data; +explain vectorization only detail +select insert_num,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,b from table_change_numeric_group_string_group_floating_string_group; + select insert_num,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,b from table_change_numeric_group_string_group_floating_string_group; -- Table-Non-Cascade CHANGE COLUMNS ... @@ -193,6 +216,9 @@ insert into table table_change_numeric_group_string_group_floating_string_group 'filler', 'filler', 'filler', 'filler', 'filler', 'filler', 'new'); +explain vectorization only detail +select insert_num,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,b from table_change_numeric_group_string_group_floating_string_group; + select insert_num,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,b from table_change_numeric_group_string_group_floating_string_group; drop table table_change_numeric_group_string_group_floating_string_group; @@ -217,6 +243,9 @@ insert into table table_change_string_group_string_group_string SELECT insert_nu string2, string2, string2, 'original' FROM schema_evolution_data; +explain vectorization only detail +select insert_num,c1,c2,c3,c4,b from table_change_string_group_string_group_string; + select insert_num,c1,c2,c3,c4,b from table_change_string_group_string_group_string; -- Table-Non-Cascade CHANGE COLUMNS ... @@ -231,6 +260,9 @@ insert into table table_change_string_group_string_group_string VALUES (111, 'filler', 'filler', 'filler', 'new'); +explain vectorization only detail +select insert_num,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,b from table_change_string_group_string_group_string; + select insert_num,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,b from table_change_string_group_string_group_string; drop table table_change_string_group_string_group_string; @@ -262,6 +294,9 @@ insert into table table_change_lower_to_higher_numeric_group_tinyint_to_bigint S bigint1, bigint1, bigint1, 'original' FROM schema_evolution_data; +explain vectorization only detail +select insert_num,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,c16,c17,c18,b from table_change_lower_to_higher_numeric_group_tinyint_to_bigint; + select insert_num,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,c16,c17,c18,b from table_change_lower_to_higher_numeric_group_tinyint_to_bigint; -- Table-Non-Cascade CHANGE COLUMNS ... @@ -279,6 +314,9 @@ insert into table table_change_lower_to_higher_numeric_group_tinyint_to_bigint V 1234.5678, 9876.543, 789.321, 'new'); +explain vectorization only detail +select insert_num,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,c16,c17,c18,b from table_change_lower_to_higher_numeric_group_tinyint_to_bigint; + select insert_num,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,c16,c17,c18,b from table_change_lower_to_higher_numeric_group_tinyint_to_bigint; drop table table_change_lower_to_higher_numeric_group_tinyint_to_bigint; @@ -300,6 +338,9 @@ insert into table table_change_lower_to_higher_numeric_group_decimal_to_float SE float1, 'original' FROM schema_evolution_data; +explain vectorization only detail +select insert_num,c1,c2,c3,b from table_change_lower_to_higher_numeric_group_decimal_to_float; + select insert_num,c1,c2,c3,b from table_change_lower_to_higher_numeric_group_decimal_to_float; -- Table-Non-Cascade CHANGE COLUMNS ... @@ -307,6 +348,9 @@ alter table table_change_lower_to_higher_numeric_group_decimal_to_float replace insert into table table_change_lower_to_higher_numeric_group_decimal_to_float VALUES (111, 1234.5678, 9876.543, 1234.5678, 'new'); +explain vectorization only detail +select insert_num,c1,c2,c3,b from table_change_lower_to_higher_numeric_group_decimal_to_float; + select insert_num,c1,c2,c3,b from table_change_lower_to_higher_numeric_group_decimal_to_float; drop table table_change_lower_to_higher_numeric_group_decimal_to_float; diff --git ql/src/test/queries/clientpositive/schema_evol_orc_acidvec_table_update.q ql/src/test/queries/clientpositive/schema_evol_orc_acidvec_table_update.q index 4858eb3..8174e38 100644 --- ql/src/test/queries/clientpositive/schema_evol_orc_acidvec_table_update.q +++ ql/src/test/queries/clientpositive/schema_evol_orc_acidvec_table_update.q @@ -1,3 +1,5 @@ +set hive.explain.user=false; +set hive.fetch.task.conversion=none; set hive.cli.print.header=true; set hive.support.concurrency=true; set hive.txn.manager=org.apache.hadoop.hive.ql.lockmgr.DbTxnManager; @@ -6,7 +8,6 @@ SET hive.exec.schema.evolution=false; SET hive.vectorized.use.vectorized.input.format=true; SET hive.vectorized.use.vector.serde.deserialize=false; SET hive.vectorized.use.row.serde.deserialize=false; -set hive.fetch.task.conversion=none; SET hive.vectorized.execution.enabled=true; set hive.exec.dynamic.partition.mode=nonstrict; set hive.metastore.disallow.incompatible.col.type.changes=true; diff --git ql/src/test/queries/clientpositive/schema_evol_orc_nonvec_part.q ql/src/test/queries/clientpositive/schema_evol_orc_nonvec_part.q index 7821c45..c4acf27 100644 --- ql/src/test/queries/clientpositive/schema_evol_orc_nonvec_part.q +++ ql/src/test/queries/clientpositive/schema_evol_orc_nonvec_part.q @@ -1,11 +1,11 @@ -set hive.explain.user=true; +set hive.explain.user=false; +set hive.fetch.task.conversion=none; set hive.mapred.mode=nonstrict; set hive.cli.print.header=true; SET hive.exec.schema.evolution=true; SET hive.vectorized.use.vectorized.input.format=true; SET hive.vectorized.use.vector.serde.deserialize=false; SET hive.vectorized.use.row.serde.deserialize=false; -set hive.fetch.task.conversion=none; SET hive.vectorized.execution.enabled=false; set hive.exec.dynamic.partition.mode=nonstrict; set hive.metastore.disallow.incompatible.col.type.changes=true; @@ -37,7 +37,7 @@ alter table part_add_int_permute_select add columns(c int); insert into table part_add_int_permute_select partition(part=1) VALUES (2, 2222, 'new', 3333); -explain +explain vectorization detail select insert_num,part,a,b from part_add_int_permute_select; -- SELECT permutation columns to make sure NULL defaulting works right @@ -60,7 +60,7 @@ alter table part_add_int_string_permute_select add columns(c int, d string); insert into table part_add_int_string_permute_select partition(part=1) VALUES (2, 2222, 'new', 3333, '4444'); -explain +explain vectorization detail select insert_num,part,a,b from part_add_int_string_permute_select; -- SELECT permutation columns to make sure NULL defaulting works right @@ -92,7 +92,7 @@ alter table part_change_string_group_double replace columns (insert_num int, c1 insert into table part_change_string_group_double partition(part=1) SELECT insert_num, double1, double1, double1, 'new' FROM schema_evolution_data WHERE insert_num = 111; -explain +explain vectorization detail select insert_num,part,c1,c2,c3,b from part_change_string_group_double; select insert_num,part,c1,c2,c3,b from part_change_string_group_double; @@ -115,7 +115,7 @@ alter table part_change_date_group_string_group_date_timestamp replace columns(i insert into table part_change_date_group_string_group_date_timestamp partition(part=1) VALUES (111, 'filler', 'filler', 'filler', 'filler', 'filler', 'filler', 'filler', 'filler', 'filler', 'filler', 'new'); -explain +explain vectorization detail select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,b from part_change_date_group_string_group_date_timestamp; select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,b from part_change_date_group_string_group_date_timestamp; @@ -163,7 +163,7 @@ insert into table part_change_numeric_group_string_group_multi_ints_string_group 'filler', 'filler', 'filler', 'filler', 'filler', 'filler', 'filler', 'filler', 'new'); -explain +explain vectorization detail select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,c16,c17,c18,c19,c20,b from part_change_numeric_group_string_group_multi_ints_string_group; select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,c16,c17,c18,c19,c20,b from part_change_numeric_group_string_group_multi_ints_string_group; @@ -206,7 +206,7 @@ insert into table part_change_numeric_group_string_group_floating_string_group p 'filler', 'filler', 'filler', 'filler', 'filler', 'filler', 'new'); -explain +explain vectorization detail select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,b from part_change_numeric_group_string_group_floating_string_group; select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,b from part_change_numeric_group_string_group_floating_string_group; @@ -248,7 +248,7 @@ insert into table part_change_string_group_string_group_string partition(part=1) 'filler', 'filler', 'filler', 'new'); -explain +explain vectorization detail select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,b from part_change_string_group_string_group_string; select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,b from part_change_string_group_string_group_string; @@ -298,7 +298,7 @@ insert into table part_change_lower_to_higher_numeric_group_tinyint_to_bigint pa 1234.5678, 9876.543, 789.321, 'new'); -explain +explain vectorization detail select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,c16,c17,c18,b from part_change_lower_to_higher_numeric_group_tinyint_to_bigint; select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,c16,c17,c18,b from part_change_lower_to_higher_numeric_group_tinyint_to_bigint; @@ -329,7 +329,7 @@ alter table part_change_lower_to_higher_numeric_group_decimal_to_float replace c insert into table part_change_lower_to_higher_numeric_group_decimal_to_float partition(part=1) VALUES (111, 1234.5678, 9876.543, 1234.5678, 'new'); -explain +explain vectorization detail select insert_num,part,c1,c2,c3,b from part_change_lower_to_higher_numeric_group_decimal_to_float; select insert_num,part,c1,c2,c3,b from part_change_lower_to_higher_numeric_group_decimal_to_float; diff --git ql/src/test/queries/clientpositive/schema_evol_orc_nonvec_part_all_complex.q ql/src/test/queries/clientpositive/schema_evol_orc_nonvec_part_all_complex.q index 90519e7..614a5be 100644 --- ql/src/test/queries/clientpositive/schema_evol_orc_nonvec_part_all_complex.q +++ ql/src/test/queries/clientpositive/schema_evol_orc_nonvec_part_all_complex.q @@ -1,11 +1,11 @@ -set hive.explain.user=true; +set hive.explain.user=false; +set hive.fetch.task.conversion=none; set hive.mapred.mode=nonstrict; set hive.cli.print.header=true; SET hive.exec.schema.evolution=true; SET hive.vectorized.use.vectorized.input.format=true; SET hive.vectorized.use.vector.serde.deserialize=false; SET hive.vectorized.use.row.serde.deserialize=false; -set hive.fetch.task.conversion=none; SET hive.vectorized.execution.enabled=false; set hive.exec.dynamic.partition.mode=nonstrict; set hive.metastore.disallow.incompatible.col.type.changes=false; @@ -51,7 +51,7 @@ load data local inpath '../../data/files/schema_evolution/complex_struct1_c.txt' insert into table part_change_various_various_struct1 partition(part=1) select * from complex_struct1_c_txt; -explain +explain vectorization detail select insert_num,part,s1,b from part_change_various_various_struct1; select insert_num,part,s1,b from part_change_various_various_struct1; @@ -111,7 +111,7 @@ load data local inpath '../../data/files/schema_evolution/complex_struct2_d.txt' insert into table part_add_various_various_struct2 partition(part=1) select * from complex_struct2_d_txt; -explain +explain vectorization detail select insert_num,part,b,s2 from part_add_various_various_struct2; select insert_num,part,b,s2 from part_add_various_various_struct2; @@ -155,7 +155,7 @@ load data local inpath '../../data/files/schema_evolution/complex_struct4_c.txt' insert into table part_add_to_various_various_struct4 partition(part=1) select * from complex_struct4_c_txt; -explain +explain vectorization detail select insert_num,part,b,s3 from part_add_to_various_various_struct4; select insert_num,part,b,s3 from part_add_to_various_various_struct4; diff --git ql/src/test/queries/clientpositive/schema_evol_orc_nonvec_part_all_primitive.q ql/src/test/queries/clientpositive/schema_evol_orc_nonvec_part_all_primitive.q index af6847e..c2d8308 100644 --- ql/src/test/queries/clientpositive/schema_evol_orc_nonvec_part_all_primitive.q +++ ql/src/test/queries/clientpositive/schema_evol_orc_nonvec_part_all_primitive.q @@ -1,11 +1,11 @@ -set hive.explain.user=true; +set hive.explain.user=false; +set hive.fetch.task.conversion=none; set hive.mapred.mode=nonstrict; set hive.cli.print.header=true; SET hive.exec.schema.evolution=true; SET hive.vectorized.use.vectorized.input.format=true; SET hive.vectorized.use.vector.serde.deserialize=false; SET hive.vectorized.use.row.serde.deserialize=false; -set hive.fetch.task.conversion=none; SET hive.vectorized.execution.enabled=false; set hive.exec.dynamic.partition.mode=nonstrict; set hive.metastore.disallow.incompatible.col.type.changes=false; @@ -72,7 +72,7 @@ insert into table part_change_various_various_boolean_to_bigint partition(part=1 bigint1, bigint1, bigint1, bigint1, bigint1, bigint1, bigint1, bigint1, bigint1, bigint1, bigint1, 'new' FROM schema_evolution_data; -explain +explain vectorization detail select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,c16,c17,c18,c19,c20,c21,c22,c23,c24,c25,c26,c27,c28,c29,c30,c31,c32,c33,c34,c35,c36,c37,c38,c39,c40,c41,c42,c43,c44,c45,c46,c47,c48,c49,c50,c51,c52,c53,b from part_change_various_various_boolean_to_bigint; select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,c16,c17,c18,c19,c20,c21,c22,c23,c24,c25,c26,c27,c28,c29,c30,c31,c32,c33,c34,c35,c36,c37,c38,c39,c40,c41,c42,c43,c44,c45,c46,c47,c48,c49,c50,c51,c52,c53,b from part_change_various_various_boolean_to_bigint; @@ -114,7 +114,7 @@ insert into table part_change_various_various_decimal_to_double partition(part=1 double1, double1, double1, double1, double1, double1, double1, double1, double1, double1, double1, 'new' FROM schema_evolution_data_2 WHERE insert_num=111; -explain +explain vectorization detail select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,c16,c17,c18,c19,c20,c21,c22,c23,c24,c25,c26,c27,c28,c29,c30,c31,c32,c33,b from part_change_various_various_decimal_to_double; select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,c16,c17,c18,c19,c20,c21,c22,c23,c24,c25,c26,c27,c28,c29,c30,c31,c32,c33,b from part_change_various_various_decimal_to_double; @@ -138,7 +138,7 @@ alter table part_change_various_various_timestamp replace columns (insert_num in insert into table part_change_various_various_timestamp partition(part=1) SELECT insert_num, timestamp1, timestamp1, timestamp1, timestamp1, timestamp1, timestamp1, timestamp1, timestamp1, timestamp1, timestamp1, timestamp1, timestamp1, 'new' FROM schema_evolution_data_2 WHERE insert_num=111; -explain +explain vectorization detail select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,b from part_change_various_various_timestamp; select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,b from part_change_various_various_timestamp; @@ -159,7 +159,7 @@ alter table part_change_various_various_date replace columns (insert_num int, c1 insert into table part_change_various_various_date partition(part=1) SELECT insert_num, date1, date1, date1, date1, 'new' FROM schema_evolution_data_2 WHERE insert_num=111; -explain +explain vectorization detail select insert_num,part,c1,c2,c3,c4,b from part_change_various_various_date; select insert_num,part,c1,c2,c3,c4,b from part_change_various_various_date; @@ -198,7 +198,7 @@ load data local inpath '../../data/files/schema_evolution/same_type1_c.txt' over insert into table part_change_same_type_different_params partition(part=2) select * from same_type1_c_txt; -explain +explain vectorization detail select insert_num,part,c1,c2,c3,c4,c5,c6,b from part_change_same_type_different_params; select insert_num,part,c1,c2,c3,c4,c5,c6,b from part_change_same_type_different_params; diff --git ql/src/test/queries/clientpositive/schema_evol_orc_nonvec_table.q ql/src/test/queries/clientpositive/schema_evol_orc_nonvec_table.q index 3fe338a..592b400 100644 --- ql/src/test/queries/clientpositive/schema_evol_orc_nonvec_table.q +++ ql/src/test/queries/clientpositive/schema_evol_orc_nonvec_table.q @@ -1,4 +1,5 @@ -set hive.explain.user=true; +set hive.explain.user=false; +set hive.fetch.task.conversion=none; set hive.cli.print.header=true; SET hive.exec.schema.evolution=true; SET hive.vectorized.use.vectorized.input.format=true; @@ -6,7 +7,6 @@ SET hive.vectorized.use.vector.serde.deserialize=false; SET hive.vectorized.use.row.serde.deserialize=false; set hive.fetch.task.conversion=none; SET hive.vectorized.execution.enabled=false; -set hive.fetch.task.conversion=none; set hive.exec.dynamic.partition.mode=nonstrict; set hive.metastore.disallow.incompatible.col.type.changes=true; set hive.default.fileformat=orc; @@ -37,7 +37,7 @@ alter table table_add_int_permute_select add columns(c int); insert into table table_add_int_permute_select VALUES (111, 80000, 'new', 80000); -explain +explain vectorization detail select insert_num,a,b from table_add_int_permute_select; -- SELECT permutation columns to make sure NULL defaulting works right @@ -60,7 +60,7 @@ alter table table_add_int_string_permute_select add columns(c int, d string); insert into table table_add_int_string_permute_select VALUES (111, 80000, 'new', 80000, 'filler'); -explain +explain vectorization detail select insert_num,a,b from table_add_int_string_permute_select; -- SELECT permutation columns to make sure NULL defaulting works right @@ -92,7 +92,7 @@ alter table table_change_string_group_double replace columns (insert_num int, c1 insert into table table_change_string_group_double VALUES (111, 789.321, 789.321, 789.321, 'new'); -explain +explain vectorization detail select insert_num,c1,c2,c3,b from table_change_string_group_double; select insert_num,c1,c2,c3,b from table_change_string_group_double; @@ -159,7 +159,7 @@ insert into table table_change_numeric_group_string_group_multi_ints_string_grou 'filler', 'filler', 'filler', 'filler', 'filler', 'filler', 'filler', 'filler', 'new'); -explain +explain vectorization detail select insert_num,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,c16,c17,c18,c19,c20,b from table_change_numeric_group_string_group_multi_ints_string_group; select insert_num,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,c16,c17,c18,c19,c20,b from table_change_numeric_group_string_group_multi_ints_string_group; @@ -202,7 +202,7 @@ insert into table table_change_numeric_group_string_group_floating_string_group 'filler', 'filler', 'filler', 'filler', 'filler', 'filler', 'new'); -explain +explain vectorization detail select insert_num,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,b from table_change_numeric_group_string_group_floating_string_group; select insert_num,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,b from table_change_numeric_group_string_group_floating_string_group; diff --git ql/src/test/queries/clientpositive/schema_evol_orc_vec_part.q ql/src/test/queries/clientpositive/schema_evol_orc_vec_part.q index 48903d2..d814870 100644 --- ql/src/test/queries/clientpositive/schema_evol_orc_vec_part.q +++ ql/src/test/queries/clientpositive/schema_evol_orc_vec_part.q @@ -1,11 +1,11 @@ set hive.explain.user=false; +set hive.fetch.task.conversion=none; set hive.mapred.mode=nonstrict; set hive.cli.print.header=true; SET hive.exec.schema.evolution=true; SET hive.vectorized.use.vectorized.input.format=true; SET hive.vectorized.use.vector.serde.deserialize=false; SET hive.vectorized.use.row.serde.deserialize=false; -set hive.fetch.task.conversion=none; SET hive.vectorized.execution.enabled=true; set hive.fetch.task.conversion=none; set hive.exec.dynamic.partition.mode=nonstrict; diff --git ql/src/test/queries/clientpositive/schema_evol_orc_vec_part_all_complex.q ql/src/test/queries/clientpositive/schema_evol_orc_vec_part_all_complex.q index 45afd9d..bff7cca 100644 --- ql/src/test/queries/clientpositive/schema_evol_orc_vec_part_all_complex.q +++ ql/src/test/queries/clientpositive/schema_evol_orc_vec_part_all_complex.q @@ -1,11 +1,11 @@ set hive.explain.user=false; +set hive.fetch.task.conversion=none; set hive.mapred.mode=nonstrict; set hive.cli.print.header=true; SET hive.exec.schema.evolution=true; SET hive.vectorized.use.vectorized.input.format=true; SET hive.vectorized.use.vector.serde.deserialize=false; SET hive.vectorized.use.row.serde.deserialize=false; -set hive.fetch.task.conversion=none; SET hive.vectorized.execution.enabled=true; set hive.exec.dynamic.partition.mode=nonstrict; set hive.metastore.disallow.incompatible.col.type.changes=false; diff --git ql/src/test/queries/clientpositive/schema_evol_orc_vec_part_all_primitive.q ql/src/test/queries/clientpositive/schema_evol_orc_vec_part_all_primitive.q index b266a67..76ab011 100644 --- ql/src/test/queries/clientpositive/schema_evol_orc_vec_part_all_primitive.q +++ ql/src/test/queries/clientpositive/schema_evol_orc_vec_part_all_primitive.q @@ -1,11 +1,11 @@ set hive.explain.user=false; +set hive.fetch.task.conversion=none; set hive.mapred.mode=nonstrict; set hive.cli.print.header=true; SET hive.exec.schema.evolution=true; SET hive.vectorized.use.vectorized.input.format=true; SET hive.vectorized.use.vector.serde.deserialize=false; SET hive.vectorized.use.row.serde.deserialize=false; -set hive.fetch.task.conversion=none; SET hive.vectorized.execution.enabled=true; set hive.exec.dynamic.partition.mode=nonstrict; set hive.metastore.disallow.incompatible.col.type.changes=false; diff --git ql/src/test/queries/clientpositive/schema_evol_orc_vec_table.q ql/src/test/queries/clientpositive/schema_evol_orc_vec_table.q index 866942e..617c76e 100644 --- ql/src/test/queries/clientpositive/schema_evol_orc_vec_table.q +++ ql/src/test/queries/clientpositive/schema_evol_orc_vec_table.q @@ -1,10 +1,10 @@ set hive.explain.user=false; +set hive.fetch.task.conversion=none; set hive.cli.print.header=true; SET hive.exec.schema.evolution=true; SET hive.vectorized.use.vectorized.input.format=true; SET hive.vectorized.use.vector.serde.deserialize=false; SET hive.vectorized.use.row.serde.deserialize=false; -set hive.fetch.task.conversion=none; SET hive.vectorized.execution.enabled=true; set hive.exec.dynamic.partition.mode=nonstrict; set hive.metastore.disallow.incompatible.col.type.changes=true; diff --git ql/src/test/queries/clientpositive/schema_evol_text_nonvec_part.q ql/src/test/queries/clientpositive/schema_evol_text_nonvec_part.q index 1e749ee..6746fae 100644 --- ql/src/test/queries/clientpositive/schema_evol_text_nonvec_part.q +++ ql/src/test/queries/clientpositive/schema_evol_text_nonvec_part.q @@ -1,11 +1,11 @@ -set hive.explain.user=true; +set hive.explain.user=false; +set hive.fetch.task.conversion=none; set hive.mapred.mode=nonstrict; set hive.cli.print.header=true; SET hive.exec.schema.evolution=true; SET hive.vectorized.use.vectorized.input.format=true; SET hive.vectorized.use.vector.serde.deserialize=false; SET hive.vectorized.use.row.serde.deserialize=false; -set hive.fetch.task.conversion=none; SET hive.vectorized.execution.enabled=false; set hive.exec.dynamic.partition.mode=nonstrict; set hive.metastore.disallow.incompatible.col.type.changes=true; @@ -37,7 +37,7 @@ alter table part_add_int_permute_select add columns(c int); insert into table part_add_int_permute_select partition(part=1) VALUES (2, 2222, 'new', 3333); -explain +explain vectorization detail select insert_num,part,a,b from part_add_int_permute_select; -- SELECT permutation columns to make sure NULL defaulting works right @@ -60,7 +60,7 @@ alter table part_add_int_string_permute_select add columns(c int, d string); insert into table part_add_int_string_permute_select partition(part=1) VALUES (2, 2222, 'new', 3333, '4444'); -explain +explain vectorization detail select insert_num,part,a,b from part_add_int_string_permute_select; -- SELECT permutation columns to make sure NULL defaulting works right @@ -92,7 +92,7 @@ alter table part_change_string_group_double replace columns (insert_num int, c1 insert into table part_change_string_group_double partition(part=1) SELECT insert_num, double1, double1, double1, 'new' FROM schema_evolution_data WHERE insert_num = 111; -explain +explain vectorization detail select insert_num,part,c1,c2,c3,b from part_change_string_group_double; select insert_num,part,c1,c2,c3,b from part_change_string_group_double; @@ -115,7 +115,7 @@ alter table part_change_date_group_string_group_date_timestamp replace columns(i insert into table part_change_date_group_string_group_date_timestamp partition(part=1) VALUES (111, 'filler', 'filler', 'filler', 'filler', 'filler', 'filler', 'filler', 'filler', 'filler', 'filler', 'new'); -explain +explain vectorization detail select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,b from part_change_date_group_string_group_date_timestamp; select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,b from part_change_date_group_string_group_date_timestamp; @@ -163,7 +163,7 @@ insert into table part_change_numeric_group_string_group_multi_ints_string_group 'filler', 'filler', 'filler', 'filler', 'filler', 'filler', 'filler', 'filler', 'new'); -explain +explain vectorization detail select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,c16,c17,c18,c19,c20,b from part_change_numeric_group_string_group_multi_ints_string_group; select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,c16,c17,c18,c19,c20,b from part_change_numeric_group_string_group_multi_ints_string_group; @@ -206,7 +206,7 @@ insert into table part_change_numeric_group_string_group_floating_string_group p 'filler', 'filler', 'filler', 'filler', 'filler', 'filler', 'new'); -explain +explain vectorization detail select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,b from part_change_numeric_group_string_group_floating_string_group; select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,b from part_change_numeric_group_string_group_floating_string_group; @@ -248,7 +248,7 @@ insert into table part_change_string_group_string_group_string partition(part=1) 'filler', 'filler', 'filler', 'new'); -explain +explain vectorization detail select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,b from part_change_string_group_string_group_string; select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,b from part_change_string_group_string_group_string; @@ -298,7 +298,7 @@ insert into table part_change_lower_to_higher_numeric_group_tinyint_to_bigint pa 1234.5678, 9876.543, 789.321, 'new'); -explain +explain vectorization detail select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,c16,c17,c18,b from part_change_lower_to_higher_numeric_group_tinyint_to_bigint; select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,c16,c17,c18,b from part_change_lower_to_higher_numeric_group_tinyint_to_bigint; @@ -329,7 +329,7 @@ alter table part_change_lower_to_higher_numeric_group_decimal_to_float replace c insert into table part_change_lower_to_higher_numeric_group_decimal_to_float partition(part=1) VALUES (111, 1234.5678, 9876.543, 1234.5678, 'new'); -explain +explain vectorization detail select insert_num,part,c1,c2,c3,b from part_change_lower_to_higher_numeric_group_decimal_to_float; select insert_num,part,c1,c2,c3,b from part_change_lower_to_higher_numeric_group_decimal_to_float; diff --git ql/src/test/queries/clientpositive/schema_evol_text_nonvec_part_all_complex.q ql/src/test/queries/clientpositive/schema_evol_text_nonvec_part_all_complex.q index 2a19e24..7c846e7 100644 --- ql/src/test/queries/clientpositive/schema_evol_text_nonvec_part_all_complex.q +++ ql/src/test/queries/clientpositive/schema_evol_text_nonvec_part_all_complex.q @@ -1,11 +1,11 @@ -set hive.explain.user=true; +set hive.explain.user=false; +set hive.fetch.task.conversion=none; set hive.mapred.mode=nonstrict; set hive.cli.print.header=true; SET hive.exec.schema.evolution=true; SET hive.vectorized.use.vectorized.input.format=true; SET hive.vectorized.use.vector.serde.deserialize=false; SET hive.vectorized.use.row.serde.deserialize=false; -set hive.fetch.task.conversion=none; SET hive.vectorized.execution.enabled=false; set hive.exec.dynamic.partition.mode=nonstrict; set hive.metastore.disallow.incompatible.col.type.changes=false; @@ -51,7 +51,7 @@ load data local inpath '../../data/files/schema_evolution/complex_struct1_c.txt' insert into table part_change_various_various_struct1 partition(part=1) select * from complex_struct1_c_txt; -explain +explain vectorization detail select insert_num,part,s1,b from part_change_various_various_struct1; select insert_num,part,s1,b from part_change_various_various_struct1; @@ -111,7 +111,7 @@ load data local inpath '../../data/files/schema_evolution/complex_struct2_d.txt' insert into table part_add_various_various_struct2 partition(part=1) select * from complex_struct2_d_txt; -explain +explain vectorization detail select insert_num,part,b,s2 from part_add_various_various_struct2; select insert_num,part,b,s2 from part_add_various_various_struct2; @@ -155,7 +155,7 @@ load data local inpath '../../data/files/schema_evolution/complex_struct4_c.txt' insert into table part_add_to_various_various_struct4 partition(part=1) select * from complex_struct4_c_txt; -explain +explain vectorization detail select insert_num,part,b,s3 from part_add_to_various_various_struct4; select insert_num,part,b,s3 from part_add_to_various_various_struct4; diff --git ql/src/test/queries/clientpositive/schema_evol_text_nonvec_part_all_primitive.q ql/src/test/queries/clientpositive/schema_evol_text_nonvec_part_all_primitive.q index 92846ec..3f2f9ed 100644 --- ql/src/test/queries/clientpositive/schema_evol_text_nonvec_part_all_primitive.q +++ ql/src/test/queries/clientpositive/schema_evol_text_nonvec_part_all_primitive.q @@ -1,11 +1,11 @@ -set hive.explain.user=true; +set hive.explain.user=false; +set hive.fetch.task.conversion=none; set hive.mapred.mode=nonstrict; set hive.cli.print.header=true; SET hive.exec.schema.evolution=true; SET hive.vectorized.use.vectorized.input.format=true; SET hive.vectorized.use.vector.serde.deserialize=false; SET hive.vectorized.use.row.serde.deserialize=false; -set hive.fetch.task.conversion=none; SET hive.vectorized.execution.enabled=false; set hive.exec.dynamic.partition.mode=nonstrict; set hive.metastore.disallow.incompatible.col.type.changes=false; @@ -72,7 +72,7 @@ insert into table part_change_various_various_boolean_to_bigint partition(part=1 bigint1, bigint1, bigint1, bigint1, bigint1, bigint1, bigint1, bigint1, bigint1, bigint1, bigint1, 'new' FROM schema_evolution_data; -explain +explain vectorization detail select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,c16,c17,c18,c19,c20,c21,c22,c23,c24,c25,c26,c27,c28,c29,c30,c31,c32,c33,c34,c35,c36,c37,c38,c39,c40,c41,c42,c43,c44,c45,c46,c47,c48,c49,c50,c51,c52,c53,b from part_change_various_various_boolean_to_bigint; select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,c16,c17,c18,c19,c20,c21,c22,c23,c24,c25,c26,c27,c28,c29,c30,c31,c32,c33,c34,c35,c36,c37,c38,c39,c40,c41,c42,c43,c44,c45,c46,c47,c48,c49,c50,c51,c52,c53,b from part_change_various_various_boolean_to_bigint; @@ -114,7 +114,7 @@ insert into table part_change_various_various_decimal_to_double partition(part=1 double1, double1, double1, double1, double1, double1, double1, double1, double1, double1, double1, 'new' FROM schema_evolution_data_2 WHERE insert_num=111; -explain +explain vectorization detail select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,c16,c17,c18,c19,c20,c21,c22,c23,c24,c25,c26,c27,c28,c29,c30,c31,c32,c33,b from part_change_various_various_decimal_to_double; select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,c16,c17,c18,c19,c20,c21,c22,c23,c24,c25,c26,c27,c28,c29,c30,c31,c32,c33,b from part_change_various_various_decimal_to_double; @@ -138,7 +138,7 @@ alter table part_change_various_various_timestamp replace columns (insert_num in insert into table part_change_various_various_timestamp partition(part=1) SELECT insert_num, timestamp1, timestamp1, timestamp1, timestamp1, timestamp1, timestamp1, timestamp1, timestamp1, timestamp1, timestamp1, timestamp1, timestamp1, 'new' FROM schema_evolution_data_2 WHERE insert_num=111; -explain +explain vectorization detail select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,b from part_change_various_various_timestamp; select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,b from part_change_various_various_timestamp; @@ -159,7 +159,7 @@ alter table part_change_various_various_date replace columns (insert_num int, c1 insert into table part_change_various_various_date partition(part=1) SELECT insert_num, date1, date1, date1, date1, 'new' FROM schema_evolution_data_2 WHERE insert_num=111; -explain +explain vectorization detail select insert_num,part,c1,c2,c3,c4,b from part_change_various_various_date; select insert_num,part,c1,c2,c3,c4,b from part_change_various_various_date; @@ -198,7 +198,7 @@ load data local inpath '../../data/files/schema_evolution/same_type1_c.txt' over insert into table part_change_same_type_different_params partition(part=2) select * from same_type1_c_txt; -explain +explain vectorization detail select insert_num,part,c1,c2,c3,c4,c5,c6,b from part_change_same_type_different_params; select insert_num,part,c1,c2,c3,c4,c5,c6,b from part_change_same_type_different_params; diff --git ql/src/test/queries/clientpositive/schema_evol_text_nonvec_table.q ql/src/test/queries/clientpositive/schema_evol_text_nonvec_table.q index c516201..ae0e001 100644 --- ql/src/test/queries/clientpositive/schema_evol_text_nonvec_table.q +++ ql/src/test/queries/clientpositive/schema_evol_text_nonvec_table.q @@ -1,10 +1,10 @@ -set hive.explain.user=true; +set hive.explain.user=false; +set hive.fetch.task.conversion=none; set hive.cli.print.header=true; SET hive.exec.schema.evolution=true; SET hive.vectorized.use.vectorized.input.format=true; SET hive.vectorized.use.vector.serde.deserialize=false; SET hive.vectorized.use.row.serde.deserialize=false; -set hive.fetch.task.conversion=none; SET hive.vectorized.execution.enabled=false; set hive.exec.dynamic.partition.mode=nonstrict; set hive.metastore.disallow.incompatible.col.type.changes=true; @@ -36,7 +36,7 @@ alter table table_add_int_permute_select add columns(c int); insert into table table_add_int_permute_select VALUES (111, 80000, 'new', 80000); -explain +explain vectorization detail select insert_num,a,b from table_add_int_permute_select; -- SELECT permutation columns to make sure NULL defaulting works right @@ -59,7 +59,7 @@ alter table table_add_int_string_permute_select add columns(c int, d string); insert into table table_add_int_string_permute_select VALUES (111, 80000, 'new', 80000, 'filler'); -explain +explain vectorization detail select insert_num,a,b from table_add_int_string_permute_select; -- SELECT permutation columns to make sure NULL defaulting works right @@ -91,7 +91,7 @@ alter table table_change_string_group_double replace columns (insert_num int, c1 insert into table table_change_string_group_double VALUES (111, 789.321, 789.321, 789.321, 'new'); -explain +explain vectorization detail select insert_num,c1,c2,c3,b from table_change_string_group_double; select insert_num,c1,c2,c3,b from table_change_string_group_double; @@ -158,7 +158,7 @@ insert into table table_change_numeric_group_string_group_multi_ints_string_grou 'filler', 'filler', 'filler', 'filler', 'filler', 'filler', 'filler', 'filler', 'new'); -explain +explain vectorization detail select insert_num,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,c16,c17,c18,c19,c20,b from table_change_numeric_group_string_group_multi_ints_string_group; select insert_num,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,c16,c17,c18,c19,c20,b from table_change_numeric_group_string_group_multi_ints_string_group; @@ -201,7 +201,7 @@ insert into table table_change_numeric_group_string_group_floating_string_group 'filler', 'filler', 'filler', 'filler', 'filler', 'filler', 'new'); -explain +explain vectorization detail select insert_num,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,b from table_change_numeric_group_string_group_floating_string_group; select insert_num,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,b from table_change_numeric_group_string_group_floating_string_group; diff --git ql/src/test/queries/clientpositive/schema_evol_text_vec_part.q ql/src/test/queries/clientpositive/schema_evol_text_vec_part.q index 77c863a..0b322b0 100644 --- ql/src/test/queries/clientpositive/schema_evol_text_vec_part.q +++ ql/src/test/queries/clientpositive/schema_evol_text_vec_part.q @@ -1,11 +1,11 @@ set hive.explain.user=false; +set hive.fetch.task.conversion=none; set hive.mapred.mode=nonstrict; set hive.cli.print.header=true; SET hive.exec.schema.evolution=true; SET hive.vectorized.use.vectorized.input.format=false; SET hive.vectorized.use.vector.serde.deserialize=true; SET hive.vectorized.use.row.serde.deserialize=false; -set hive.fetch.task.conversion=none; SET hive.vectorized.execution.enabled=true; set hive.exec.dynamic.partition.mode=nonstrict; set hive.metastore.disallow.incompatible.col.type.changes=true; diff --git ql/src/test/queries/clientpositive/schema_evol_text_vec_part_all_complex.q ql/src/test/queries/clientpositive/schema_evol_text_vec_part_all_complex.q index 7eb72e0..131a1af 100644 --- ql/src/test/queries/clientpositive/schema_evol_text_vec_part_all_complex.q +++ ql/src/test/queries/clientpositive/schema_evol_text_vec_part_all_complex.q @@ -1,11 +1,11 @@ set hive.explain.user=false; +set hive.fetch.task.conversion=none; set hive.mapred.mode=nonstrict; set hive.cli.print.header=true; SET hive.exec.schema.evolution=true; SET hive.vectorized.use.vectorized.input.format=false; SET hive.vectorized.use.vector.serde.deserialize=true; SET hive.vectorized.use.row.serde.deserialize=false; -set hive.fetch.task.conversion=none; SET hive.vectorized.execution.enabled=true; set hive.exec.dynamic.partition.mode=nonstrict; set hive.metastore.disallow.incompatible.col.type.changes=false; diff --git ql/src/test/queries/clientpositive/schema_evol_text_vec_part_all_primitive.q ql/src/test/queries/clientpositive/schema_evol_text_vec_part_all_primitive.q index d5c01cd..2448268 100644 --- ql/src/test/queries/clientpositive/schema_evol_text_vec_part_all_primitive.q +++ ql/src/test/queries/clientpositive/schema_evol_text_vec_part_all_primitive.q @@ -1,11 +1,11 @@ set hive.explain.user=false; +set hive.fetch.task.conversion=none; set hive.mapred.mode=nonstrict; set hive.cli.print.header=true; SET hive.exec.schema.evolution=true; SET hive.vectorized.use.vectorized.input.format=false; SET hive.vectorized.use.vector.serde.deserialize=true; SET hive.vectorized.use.row.serde.deserialize=false; -set hive.fetch.task.conversion=none; SET hive.vectorized.execution.enabled=true; set hive.exec.dynamic.partition.mode=nonstrict; set hive.metastore.disallow.incompatible.col.type.changes=false; diff --git ql/src/test/queries/clientpositive/schema_evol_text_vec_table.q ql/src/test/queries/clientpositive/schema_evol_text_vec_table.q index bbf03af..166b34a 100644 --- ql/src/test/queries/clientpositive/schema_evol_text_vec_table.q +++ ql/src/test/queries/clientpositive/schema_evol_text_vec_table.q @@ -1,10 +1,10 @@ set hive.explain.user=false; +set hive.fetch.task.conversion=none; set hive.cli.print.header=true; SET hive.exec.schema.evolution=true; SET hive.vectorized.use.vectorized.input.format=false; SET hive.vectorized.use.vector.serde.deserialize=true; SET hive.vectorized.use.row.serde.deserialize=false; -set hive.fetch.task.conversion=none; SET hive.vectorized.execution.enabled=true; set hive.exec.dynamic.partition.mode=nonstrict; set hive.metastore.disallow.incompatible.col.type.changes=true; diff --git ql/src/test/queries/clientpositive/schema_evol_text_vecrow_part.q ql/src/test/queries/clientpositive/schema_evol_text_vecrow_part.q index 11df12e..0ab1f33 100644 --- ql/src/test/queries/clientpositive/schema_evol_text_vecrow_part.q +++ ql/src/test/queries/clientpositive/schema_evol_text_vecrow_part.q @@ -1,11 +1,11 @@ set hive.explain.user=false; +set hive.fetch.task.conversion=none; set hive.mapred.mode=nonstrict; set hive.cli.print.header=true; SET hive.exec.schema.evolution=true; SET hive.vectorized.use.vectorized.input.format=false; SET hive.vectorized.use.vector.serde.deserialize=false; SET hive.vectorized.use.row.serde.deserialize=true; -set hive.fetch.task.conversion=none; SET hive.vectorized.execution.enabled=true; set hive.exec.dynamic.partition.mode=nonstrict; set hive.metastore.disallow.incompatible.col.type.changes=true; diff --git ql/src/test/queries/clientpositive/schema_evol_text_vecrow_part_all_complex.q ql/src/test/queries/clientpositive/schema_evol_text_vecrow_part_all_complex.q index dfd55d9..b4a9d66 100644 --- ql/src/test/queries/clientpositive/schema_evol_text_vecrow_part_all_complex.q +++ ql/src/test/queries/clientpositive/schema_evol_text_vecrow_part_all_complex.q @@ -1,11 +1,11 @@ set hive.explain.user=false; +set hive.fetch.task.conversion=none; set hive.mapred.mode=nonstrict; set hive.cli.print.header=true; SET hive.exec.schema.evolution=true; SET hive.vectorized.use.vectorized.input.format=false; SET hive.vectorized.use.vector.serde.deserialize=false; SET hive.vectorized.use.row.serde.deserialize=true; -set hive.fetch.task.conversion=none; SET hive.vectorized.execution.enabled=true; set hive.exec.dynamic.partition.mode=nonstrict; set hive.metastore.disallow.incompatible.col.type.changes=false; diff --git ql/src/test/queries/clientpositive/schema_evol_text_vecrow_part_all_primitive.q ql/src/test/queries/clientpositive/schema_evol_text_vecrow_part_all_primitive.q index d71c6b8..83fc173 100644 --- ql/src/test/queries/clientpositive/schema_evol_text_vecrow_part_all_primitive.q +++ ql/src/test/queries/clientpositive/schema_evol_text_vecrow_part_all_primitive.q @@ -1,11 +1,11 @@ set hive.explain.user=false; +set hive.fetch.task.conversion=none; set hive.mapred.mode=nonstrict; set hive.cli.print.header=true; SET hive.exec.schema.evolution=true; SET hive.vectorized.use.vectorized.input.format=false; SET hive.vectorized.use.vector.serde.deserialize=false; SET hive.vectorized.use.row.serde.deserialize=true; -set hive.fetch.task.conversion=none; SET hive.vectorized.execution.enabled=true; set hive.exec.dynamic.partition.mode=nonstrict; set hive.metastore.disallow.incompatible.col.type.changes=false; diff --git ql/src/test/queries/clientpositive/schema_evol_text_vecrow_table.q ql/src/test/queries/clientpositive/schema_evol_text_vecrow_table.q index d4209a5..3059604 100644 --- ql/src/test/queries/clientpositive/schema_evol_text_vecrow_table.q +++ ql/src/test/queries/clientpositive/schema_evol_text_vecrow_table.q @@ -1,10 +1,10 @@ set hive.explain.user=false; +set hive.fetch.task.conversion=none; set hive.cli.print.header=true; SET hive.exec.schema.evolution=true; SET hive.vectorized.use.vectorized.input.format=false; SET hive.vectorized.use.vector.serde.deserialize=false; SET hive.vectorized.use.row.serde.deserialize=true; -set hive.fetch.task.conversion=none; SET hive.vectorized.execution.enabled=true; set hive.exec.dynamic.partition.mode=nonstrict; set hive.metastore.disallow.incompatible.col.type.changes=true; diff --git ql/src/test/results/clientpositive/llap/schema_evol_orc_acid_part.q.out ql/src/test/results/clientpositive/llap/schema_evol_orc_acid_part.q.out index a3a54d1..bc9f3c8 100644 --- ql/src/test/results/clientpositive/llap/schema_evol_orc_acid_part.q.out +++ ql/src/test/results/clientpositive/llap/schema_evol_orc_acid_part.q.out @@ -138,6 +138,17 @@ POSTHOOK: Lineage: part_add_int_string_permute_select PARTITION(part=1).c EXPRES POSTHOOK: Lineage: part_add_int_string_permute_select PARTITION(part=1).d SIMPLE [(values__tmp__table__4)values__tmp__table__4.FieldSchema(name:tmp_values_col5, type:string, comment:), ] POSTHOOK: Lineage: part_add_int_string_permute_select PARTITION(part=1).insert_num EXPRESSION [(values__tmp__table__4)values__tmp__table__4.FieldSchema(name:tmp_values_col1, type:string, comment:), ] _col0 _col1 _col2 _col3 _col4 +PREHOOK: query: explain vectorization only detail +select insert_num,part,a,b,c,d from part_add_int_string_permute_select +PREHOOK: type: QUERY +POSTHOOK: query: explain vectorization only detail +select insert_num,part,a,b,c,d from part_add_int_string_permute_select +POSTHOOK: type: QUERY +Explain +PLAN VECTORIZATION: + enabled: false + enabledConditionsNotMet: [hive.vectorized.execution.enabled IS false] + PREHOOK: query: select insert_num,part,a,b from part_add_int_string_permute_select PREHOOK: type: QUERY PREHOOK: Input: default@part_add_int_string_permute_select @@ -510,46 +521,6 @@ POSTHOOK: Lineage: part_change_numeric_group_string_group_multi_ints_string_grou POSTHOOK: Lineage: part_change_numeric_group_string_group_multi_ints_string_group PARTITION(part=1).c9 EXPRESSION [(values__tmp__table__6)values__tmp__table__6.FieldSchema(name:tmp_values_col10, type:string, comment:), ] POSTHOOK: Lineage: part_change_numeric_group_string_group_multi_ints_string_group PARTITION(part=1).insert_num EXPRESSION [(values__tmp__table__6)values__tmp__table__6.FieldSchema(name:tmp_values_col1, type:string, comment:), ] _col0 _col1 _col2 _col3 _col4 _col5 _col6 _col7 _col8 _col9 _col10 _col11 _col12 _col13 _col14 _col15 _col16 _col17 _col18 _col19 _col20 _col21 -PREHOOK: query: explain -select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,c16,c17,c18,c19,c20,b from part_change_numeric_group_string_group_multi_ints_string_group -PREHOOK: type: QUERY -POSTHOOK: query: explain -select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,c16,c17,c18,c19,c20,b from part_change_numeric_group_string_group_multi_ints_string_group -POSTHOOK: type: QUERY -Explain -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Tez -#### A masked pattern was here #### - Vertices: - Map 1 - Map Operator Tree: - TableScan - alias: part_change_numeric_group_string_group_multi_ints_string_group - Statistics: Num rows: 6 Data size: 2903 Basic stats: COMPLETE Column stats: PARTIAL - Select Operator - expressions: insert_num (type: int), part (type: int), c1 (type: string), c2 (type: string), c3 (type: string), c4 (type: string), c5 (type: char(50)), c6 (type: char(50)), c7 (type: char(50)), c8 (type: char(50)), c9 (type: char(5)), c10 (type: char(5)), c11 (type: char(5)), c12 (type: char(5)), c13 (type: varchar(50)), c14 (type: varchar(50)), c15 (type: varchar(50)), c16 (type: varchar(50)), c17 (type: varchar(5)), c18 (type: varchar(5)), c19 (type: varchar(5)), c20 (type: varchar(5)), b (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL - File Output Operator - compressed: false - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL - 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 - Execution mode: llap - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - PREHOOK: query: select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,c16,c17,c18,c19,c20,b from part_change_numeric_group_string_group_multi_ints_string_group PREHOOK: type: QUERY PREHOOK: Input: default@part_change_numeric_group_string_group_multi_ints_string_group @@ -689,46 +660,6 @@ POSTHOOK: Lineage: part_change_numeric_group_string_group_floating_string_group POSTHOOK: Lineage: part_change_numeric_group_string_group_floating_string_group PARTITION(part=1).c9 EXPRESSION [(values__tmp__table__7)values__tmp__table__7.FieldSchema(name:tmp_values_col10, type:string, comment:), ] POSTHOOK: Lineage: part_change_numeric_group_string_group_floating_string_group PARTITION(part=1).insert_num EXPRESSION [(values__tmp__table__7)values__tmp__table__7.FieldSchema(name:tmp_values_col1, type:string, comment:), ] _col0 _col1 _col2 _col3 _col4 _col5 _col6 _col7 _col8 _col9 _col10 _col11 _col12 _col13 _col14 _col15 _col16 -PREHOOK: query: explain -select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,b from part_change_numeric_group_string_group_floating_string_group -PREHOOK: type: QUERY -POSTHOOK: query: explain -select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,b from part_change_numeric_group_string_group_floating_string_group -POSTHOOK: type: QUERY -Explain -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Tez -#### A masked pattern was here #### - Vertices: - Map 1 - Map Operator Tree: - TableScan - alias: part_change_numeric_group_string_group_floating_string_group - Statistics: Num rows: 6 Data size: 4540 Basic stats: COMPLETE Column stats: PARTIAL - Select Operator - expressions: insert_num (type: int), part (type: int), c1 (type: string), c2 (type: string), c3 (type: string), c4 (type: char(50)), c5 (type: char(50)), c6 (type: char(50)), c7 (type: char(7)), c8 (type: char(7)), c9 (type: char(7)), c10 (type: varchar(50)), c11 (type: varchar(50)), c12 (type: varchar(50)), c13 (type: varchar(7)), c14 (type: varchar(7)), c15 (type: varchar(7)), b (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL - File Output Operator - compressed: false - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL - 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 - Execution mode: llap - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - PREHOOK: query: select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,b from part_change_numeric_group_string_group_floating_string_group PREHOOK: type: QUERY PREHOOK: Input: default@part_change_numeric_group_string_group_floating_string_group diff --git ql/src/test/results/clientpositive/llap/schema_evol_orc_acid_table.q.out ql/src/test/results/clientpositive/llap/schema_evol_orc_acid_table.q.out index ce33ed0..1123e70 100644 --- ql/src/test/results/clientpositive/llap/schema_evol_orc_acid_table.q.out +++ ql/src/test/results/clientpositive/llap/schema_evol_orc_acid_table.q.out @@ -55,6 +55,17 @@ POSTHOOK: Lineage: table_add_int_permute_select.b SIMPLE [(values__tmp__table__1 POSTHOOK: Lineage: table_add_int_permute_select.c EXPRESSION [(values__tmp__table__1)values__tmp__table__1.FieldSchema(name:tmp_values_col4, type:string, comment:), ] POSTHOOK: Lineage: table_add_int_permute_select.insert_num EXPRESSION [(values__tmp__table__1)values__tmp__table__1.FieldSchema(name:tmp_values_col1, type:string, comment:), ] _col0 _col1 _col2 _col3 +PREHOOK: query: explain vectorization only detail +select insert_num,a,b,c from table_add_int_permute_select +PREHOOK: type: QUERY +POSTHOOK: query: explain vectorization only detail +select insert_num,a,b,c from table_add_int_permute_select +POSTHOOK: type: QUERY +Explain +PLAN VECTORIZATION: + enabled: false + enabledConditionsNotMet: [hive.vectorized.execution.enabled IS false] + PREHOOK: query: select insert_num,a,b from table_add_int_permute_select PREHOOK: type: QUERY PREHOOK: Input: default@table_add_int_permute_select diff --git ql/src/test/results/clientpositive/llap/schema_evol_orc_acidvec_part.q.out ql/src/test/results/clientpositive/llap/schema_evol_orc_acidvec_part.q.out index 81d7a24..e509a42 100644 --- ql/src/test/results/clientpositive/llap/schema_evol_orc_acidvec_part.q.out +++ ql/src/test/results/clientpositive/llap/schema_evol_orc_acidvec_part.q.out @@ -53,6 +53,56 @@ POSTHOOK: Lineage: part_add_int_permute_select PARTITION(part=1).b SIMPLE [(valu POSTHOOK: Lineage: part_add_int_permute_select PARTITION(part=1).c EXPRESSION [(values__tmp__table__2)values__tmp__table__2.FieldSchema(name:tmp_values_col4, type:string, comment:), ] POSTHOOK: Lineage: part_add_int_permute_select PARTITION(part=1).insert_num EXPRESSION [(values__tmp__table__2)values__tmp__table__2.FieldSchema(name:tmp_values_col1, type:string, comment:), ] _col0 _col1 _col2 _col3 +PREHOOK: query: explain vectorization only detail +select insert_num,part,a,b,c from part_add_int_permute_select +PREHOOK: type: QUERY +POSTHOOK: query: explain vectorization only detail +select insert_num,part,a,b,c from part_add_int_permute_select +POSTHOOK: type: QUERY +Explain +PLAN VECTORIZATION: + enabled: true + enabledConditionsMet: [hive.vectorized.execution.enabled IS true] + +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez + Vertices: + Map 1 + Map Operator Tree: + TableScan Vectorization: + native: true + projectedOutputColumns: [0, 1, 2, 3, 4] + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumns: [0, 4, 1, 2, 3] + File Sink Vectorization: + className: VectorFileSinkOperator + native: false + Execution mode: vectorized, llap + Map Vectorization: + enabled: true + enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true + groupByVectorOutput: true + inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + allNative: false + usesVectorUDFAdaptor: false + vectorized: true + rowBatchContext: + dataColumnCount: 4 + includeColumns: [0, 1, 2, 3] + dataColumns: insert_num:int, a:int, b:string, c:int + partitionColumnCount: 1 + partitionColumns: part:int + + Stage: Stage-0 + Fetch Operator + PREHOOK: query: select insert_num,part,a,b from part_add_int_permute_select PREHOOK: type: QUERY PREHOOK: Input: default@part_add_int_permute_select @@ -138,6 +188,56 @@ POSTHOOK: Lineage: part_add_int_string_permute_select PARTITION(part=1).c EXPRES POSTHOOK: Lineage: part_add_int_string_permute_select PARTITION(part=1).d SIMPLE [(values__tmp__table__4)values__tmp__table__4.FieldSchema(name:tmp_values_col5, type:string, comment:), ] POSTHOOK: Lineage: part_add_int_string_permute_select PARTITION(part=1).insert_num EXPRESSION [(values__tmp__table__4)values__tmp__table__4.FieldSchema(name:tmp_values_col1, type:string, comment:), ] _col0 _col1 _col2 _col3 _col4 +PREHOOK: query: explain vectorization only detail +select insert_num,part,a,b,c,d from part_add_int_string_permute_select +PREHOOK: type: QUERY +POSTHOOK: query: explain vectorization only detail +select insert_num,part,a,b,c,d from part_add_int_string_permute_select +POSTHOOK: type: QUERY +Explain +PLAN VECTORIZATION: + enabled: true + enabledConditionsMet: [hive.vectorized.execution.enabled IS true] + +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez + Vertices: + Map 1 + Map Operator Tree: + TableScan Vectorization: + native: true + projectedOutputColumns: [0, 1, 2, 3, 4, 5] + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumns: [0, 5, 1, 2, 3, 4] + File Sink Vectorization: + className: VectorFileSinkOperator + native: false + Execution mode: vectorized, llap + Map Vectorization: + enabled: true + enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true + groupByVectorOutput: true + inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + allNative: false + usesVectorUDFAdaptor: false + vectorized: true + rowBatchContext: + dataColumnCount: 5 + includeColumns: [0, 1, 2, 3, 4] + dataColumns: insert_num:int, a:int, b:string, c:int, d:string + partitionColumnCount: 1 + partitionColumns: part:int + + Stage: Stage-0 + Fetch Operator + PREHOOK: query: select insert_num,part,a,b from part_add_int_string_permute_select PREHOOK: type: QUERY PREHOOK: Input: default@part_add_int_string_permute_select @@ -281,6 +381,56 @@ POSTHOOK: Lineage: part_change_string_group_double PARTITION(part=1).c2 SIMPLE [ POSTHOOK: Lineage: part_change_string_group_double PARTITION(part=1).c3 SIMPLE [(schema_evolution_data)schema_evolution_data.FieldSchema(name:double1, type:double, comment:null), ] POSTHOOK: Lineage: part_change_string_group_double PARTITION(part=1).insert_num SIMPLE [(schema_evolution_data)schema_evolution_data.FieldSchema(name:insert_num, type:int, comment:null), ] insert_num double1 double1 double1 _c4 +PREHOOK: query: explain vectorization only detail +select insert_num,part,c1,c2,c3,b from part_change_string_group_double +PREHOOK: type: QUERY +POSTHOOK: query: explain vectorization only detail +select insert_num,part,c1,c2,c3,b from part_change_string_group_double +POSTHOOK: type: QUERY +Explain +PLAN VECTORIZATION: + enabled: true + enabledConditionsMet: [hive.vectorized.execution.enabled IS true] + +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez + Vertices: + Map 1 + Map Operator Tree: + TableScan Vectorization: + native: true + projectedOutputColumns: [0, 1, 2, 3, 4, 5] + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumns: [0, 5, 1, 2, 3, 4] + File Sink Vectorization: + className: VectorFileSinkOperator + native: false + Execution mode: vectorized, llap + Map Vectorization: + enabled: true + enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true + groupByVectorOutput: true + inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + allNative: false + usesVectorUDFAdaptor: false + vectorized: true + rowBatchContext: + dataColumnCount: 5 + includeColumns: [0, 1, 2, 3, 4] + dataColumns: insert_num:int, c1:double, c2:double, c3:double, b:string + partitionColumnCount: 1 + partitionColumns: part:int + + Stage: Stage-0 + Fetch Operator + PREHOOK: query: select insert_num,part,c1,c2,c3,b from part_change_string_group_double PREHOOK: type: QUERY PREHOOK: Input: default@part_change_string_group_double @@ -361,6 +511,56 @@ POSTHOOK: Lineage: part_change_date_group_string_group_date_timestamp PARTITION( POSTHOOK: Lineage: part_change_date_group_string_group_date_timestamp PARTITION(part=1).c9 EXPRESSION [(values__tmp__table__5)values__tmp__table__5.FieldSchema(name:tmp_values_col10, type:string, comment:), ] POSTHOOK: Lineage: part_change_date_group_string_group_date_timestamp PARTITION(part=1).insert_num EXPRESSION [(values__tmp__table__5)values__tmp__table__5.FieldSchema(name:tmp_values_col1, type:string, comment:), ] _col0 _col1 _col2 _col3 _col4 _col5 _col6 _col7 _col8 _col9 _col10 _col11 +PREHOOK: query: explain vectorization only detail +select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,b from part_change_date_group_string_group_date_timestamp +PREHOOK: type: QUERY +POSTHOOK: query: explain vectorization only detail +select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,b from part_change_date_group_string_group_date_timestamp +POSTHOOK: type: QUERY +Explain +PLAN VECTORIZATION: + enabled: true + enabledConditionsMet: [hive.vectorized.execution.enabled IS true] + +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez + Vertices: + Map 1 + Map Operator Tree: + TableScan Vectorization: + native: true + projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12] + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumns: [0, 12, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11] + File Sink Vectorization: + className: VectorFileSinkOperator + native: false + Execution mode: vectorized, llap + Map Vectorization: + enabled: true + enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true + groupByVectorOutput: true + inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + allNative: false + usesVectorUDFAdaptor: false + vectorized: true + rowBatchContext: + dataColumnCount: 12 + includeColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11] + dataColumns: insert_num:int, c1:string, c2:char(50), c3:char(15), c4:varchar(50), c5:varchar(15), c6:string, c7:char(50), c8:char(15), c9:varchar(50), c10:varchar(15), b:string + partitionColumnCount: 1 + partitionColumns: part:int + + Stage: Stage-0 + Fetch Operator + PREHOOK: query: select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,b from part_change_date_group_string_group_date_timestamp PREHOOK: type: QUERY PREHOOK: Input: default@part_change_date_group_string_group_date_timestamp @@ -441,6 +641,56 @@ POSTHOOK: Lineage: part_change_numeric_group_string_group_multi_ints_string_grou POSTHOOK: Lineage: part_change_numeric_group_string_group_multi_ints_string_group PARTITION(part=1).c9 SIMPLE [(schema_evolution_data)schema_evolution_data.FieldSchema(name:tinyint1, type:tinyint, comment:null), ] POSTHOOK: Lineage: part_change_numeric_group_string_group_multi_ints_string_group PARTITION(part=1).insert_num SIMPLE [(schema_evolution_data)schema_evolution_data.FieldSchema(name:insert_num, type:int, comment:null), ] insert_num tinyint1 smallint1 int1 bigint1 tinyint1 smallint1 int1 bigint1 tinyint1 smallint1 int1 bigint1 tinyint1 smallint1 int1 bigint1 tinyint1 smallint1 int1 bigint1 _c21 +PREHOOK: query: explain vectorization only detail +select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,c16,c17,c18,c19,c20,b from part_change_numeric_group_string_group_multi_ints_string_group +PREHOOK: type: QUERY +POSTHOOK: query: explain vectorization only detail +select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,c16,c17,c18,c19,c20,b from part_change_numeric_group_string_group_multi_ints_string_group +POSTHOOK: type: QUERY +Explain +PLAN VECTORIZATION: + enabled: true + enabledConditionsMet: [hive.vectorized.execution.enabled IS true] + +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez + Vertices: + Map 1 + Map Operator Tree: + TableScan Vectorization: + native: true + projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22] + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumns: [0, 22, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21] + File Sink Vectorization: + className: VectorFileSinkOperator + native: false + Execution mode: vectorized, llap + Map Vectorization: + enabled: true + enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true + groupByVectorOutput: true + inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + allNative: false + usesVectorUDFAdaptor: false + vectorized: true + rowBatchContext: + dataColumnCount: 22 + includeColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21] + dataColumns: insert_num:int, c1:tinyint, c2:smallint, c3:int, c4:bigint, c5:tinyint, c6:smallint, c7:int, c8:bigint, c9:tinyint, c10:smallint, c11:int, c12:bigint, c13:tinyint, c14:smallint, c15:int, c16:bigint, c17:tinyint, c18:smallint, c19:int, c20:bigint, b:string + partitionColumnCount: 1 + partitionColumns: part:int + + Stage: Stage-0 + Fetch Operator + PREHOOK: query: select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,c16,c17,c18,c19,c20,b from part_change_numeric_group_string_group_multi_ints_string_group PREHOOK: type: QUERY PREHOOK: Input: default@part_change_numeric_group_string_group_multi_ints_string_group @@ -510,13 +760,17 @@ POSTHOOK: Lineage: part_change_numeric_group_string_group_multi_ints_string_grou POSTHOOK: Lineage: part_change_numeric_group_string_group_multi_ints_string_group PARTITION(part=1).c9 EXPRESSION [(values__tmp__table__6)values__tmp__table__6.FieldSchema(name:tmp_values_col10, type:string, comment:), ] POSTHOOK: Lineage: part_change_numeric_group_string_group_multi_ints_string_group PARTITION(part=1).insert_num EXPRESSION [(values__tmp__table__6)values__tmp__table__6.FieldSchema(name:tmp_values_col1, type:string, comment:), ] _col0 _col1 _col2 _col3 _col4 _col5 _col6 _col7 _col8 _col9 _col10 _col11 _col12 _col13 _col14 _col15 _col16 _col17 _col18 _col19 _col20 _col21 -PREHOOK: query: explain +PREHOOK: query: explain vectorization only detail select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,c16,c17,c18,c19,c20,b from part_change_numeric_group_string_group_multi_ints_string_group PREHOOK: type: QUERY -POSTHOOK: query: explain +POSTHOOK: query: explain vectorization only detail select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,c16,c17,c18,c19,c20,b from part_change_numeric_group_string_group_multi_ints_string_group POSTHOOK: type: QUERY Explain +PLAN VECTORIZATION: + enabled: true + enabledConditionsMet: [hive.vectorized.execution.enabled IS true] + STAGE DEPENDENCIES: Stage-1 is a root stage Stage-0 depends on stages: Stage-1 @@ -524,31 +778,37 @@ STAGE DEPENDENCIES: STAGE PLANS: Stage: Stage-1 Tez -#### A masked pattern was here #### Vertices: Map 1 Map Operator Tree: - TableScan - alias: part_change_numeric_group_string_group_multi_ints_string_group - Statistics: Num rows: 6 Data size: 2903 Basic stats: COMPLETE Column stats: PARTIAL - Select Operator - expressions: insert_num (type: int), part (type: int), c1 (type: string), c2 (type: string), c3 (type: string), c4 (type: string), c5 (type: char(50)), c6 (type: char(50)), c7 (type: char(50)), c8 (type: char(50)), c9 (type: char(5)), c10 (type: char(5)), c11 (type: char(5)), c12 (type: char(5)), c13 (type: varchar(50)), c14 (type: varchar(50)), c15 (type: varchar(50)), c16 (type: varchar(50)), c17 (type: varchar(5)), c18 (type: varchar(5)), c19 (type: varchar(5)), c20 (type: varchar(5)), b (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL - File Output Operator - compressed: false - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL - 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 + TableScan Vectorization: + native: true + projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22] + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumns: [0, 22, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21] + File Sink Vectorization: + className: VectorFileSinkOperator + native: false Execution mode: vectorized, llap + Map Vectorization: + enabled: true + enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true + groupByVectorOutput: true + inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + allNative: false + usesVectorUDFAdaptor: false + vectorized: true + rowBatchContext: + dataColumnCount: 22 + includeColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21] + dataColumns: insert_num:int, c1:string, c2:string, c3:string, c4:string, c5:char(50), c6:char(50), c7:char(50), c8:char(50), c9:char(5), c10:char(5), c11:char(5), c12:char(5), c13:varchar(50), c14:varchar(50), c15:varchar(50), c16:varchar(50), c17:varchar(5), c18:varchar(5), c19:varchar(5), c20:varchar(5), b:string + partitionColumnCount: 1 + partitionColumns: part:int Stage: Stage-0 Fetch Operator - limit: -1 - Processor Tree: - ListSink PREHOOK: query: select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,c16,c17,c18,c19,c20,b from part_change_numeric_group_string_group_multi_ints_string_group PREHOOK: type: QUERY @@ -625,6 +885,56 @@ POSTHOOK: Lineage: part_change_numeric_group_string_group_floating_string_group POSTHOOK: Lineage: part_change_numeric_group_string_group_floating_string_group PARTITION(part=1).c9 SIMPLE [(schema_evolution_data)schema_evolution_data.FieldSchema(name:double1, type:double, comment:null), ] POSTHOOK: Lineage: part_change_numeric_group_string_group_floating_string_group PARTITION(part=1).insert_num SIMPLE [(schema_evolution_data)schema_evolution_data.FieldSchema(name:insert_num, type:int, comment:null), ] insert_num decimal1 float1 double1 decimal1 float1 double1 decimal1 float1 double1 decimal1 float1 double1 decimal1 float1 double1 _c16 +PREHOOK: query: explain vectorization only detail +select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,b from part_change_numeric_group_string_group_floating_string_group +PREHOOK: type: QUERY +POSTHOOK: query: explain vectorization only detail +select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,b from part_change_numeric_group_string_group_floating_string_group +POSTHOOK: type: QUERY +Explain +PLAN VECTORIZATION: + enabled: true + enabledConditionsMet: [hive.vectorized.execution.enabled IS true] + +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez + Vertices: + Map 1 + Map Operator Tree: + TableScan Vectorization: + native: true + projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17] + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumns: [0, 17, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16] + File Sink Vectorization: + className: VectorFileSinkOperator + native: false + Execution mode: vectorized, llap + Map Vectorization: + enabled: true + enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true + groupByVectorOutput: true + inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + allNative: false + usesVectorUDFAdaptor: false + vectorized: true + rowBatchContext: + dataColumnCount: 17 + includeColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16] + dataColumns: insert_num:int, c1:decimal(38,18), c2:float, c3:double, c4:decimal(38,18), c5:float, c6:double, c7:decimal(38,18), c8:float, c9:double, c10:decimal(38,18), c11:float, c12:double, c13:decimal(38,18), c14:float, c15:double, b:string + partitionColumnCount: 1 + partitionColumns: part:int + + Stage: Stage-0 + Fetch Operator + PREHOOK: query: select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,b from part_change_numeric_group_string_group_floating_string_group PREHOOK: type: QUERY PREHOOK: Input: default@part_change_numeric_group_string_group_floating_string_group @@ -689,13 +999,17 @@ POSTHOOK: Lineage: part_change_numeric_group_string_group_floating_string_group POSTHOOK: Lineage: part_change_numeric_group_string_group_floating_string_group PARTITION(part=1).c9 EXPRESSION [(values__tmp__table__7)values__tmp__table__7.FieldSchema(name:tmp_values_col10, type:string, comment:), ] POSTHOOK: Lineage: part_change_numeric_group_string_group_floating_string_group PARTITION(part=1).insert_num EXPRESSION [(values__tmp__table__7)values__tmp__table__7.FieldSchema(name:tmp_values_col1, type:string, comment:), ] _col0 _col1 _col2 _col3 _col4 _col5 _col6 _col7 _col8 _col9 _col10 _col11 _col12 _col13 _col14 _col15 _col16 -PREHOOK: query: explain +PREHOOK: query: explain vectorization only detail select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,b from part_change_numeric_group_string_group_floating_string_group PREHOOK: type: QUERY -POSTHOOK: query: explain +POSTHOOK: query: explain vectorization only detail select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,b from part_change_numeric_group_string_group_floating_string_group POSTHOOK: type: QUERY Explain +PLAN VECTORIZATION: + enabled: true + enabledConditionsMet: [hive.vectorized.execution.enabled IS true] + STAGE DEPENDENCIES: Stage-1 is a root stage Stage-0 depends on stages: Stage-1 @@ -703,31 +1017,37 @@ STAGE DEPENDENCIES: STAGE PLANS: Stage: Stage-1 Tez -#### A masked pattern was here #### Vertices: Map 1 Map Operator Tree: - TableScan - alias: part_change_numeric_group_string_group_floating_string_group - Statistics: Num rows: 6 Data size: 4540 Basic stats: COMPLETE Column stats: PARTIAL - Select Operator - expressions: insert_num (type: int), part (type: int), c1 (type: string), c2 (type: string), c3 (type: string), c4 (type: char(50)), c5 (type: char(50)), c6 (type: char(50)), c7 (type: char(7)), c8 (type: char(7)), c9 (type: char(7)), c10 (type: varchar(50)), c11 (type: varchar(50)), c12 (type: varchar(50)), c13 (type: varchar(7)), c14 (type: varchar(7)), c15 (type: varchar(7)), b (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL - File Output Operator - compressed: false - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL - 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 + TableScan Vectorization: + native: true + projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17] + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumns: [0, 17, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16] + File Sink Vectorization: + className: VectorFileSinkOperator + native: false Execution mode: vectorized, llap + Map Vectorization: + enabled: true + enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true + groupByVectorOutput: true + inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + allNative: false + usesVectorUDFAdaptor: false + vectorized: true + rowBatchContext: + dataColumnCount: 17 + includeColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16] + dataColumns: insert_num:int, c1:string, c2:string, c3:string, c4:char(50), c5:char(50), c6:char(50), c7:char(7), c8:char(7), c9:char(7), c10:varchar(50), c11:varchar(50), c12:varchar(50), c13:varchar(7), c14:varchar(7), c15:varchar(7), b:string + partitionColumnCount: 1 + partitionColumns: part:int Stage: Stage-0 Fetch Operator - limit: -1 - Processor Tree: - ListSink PREHOOK: query: select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,b from part_change_numeric_group_string_group_floating_string_group PREHOOK: type: QUERY @@ -797,6 +1117,56 @@ POSTHOOK: Lineage: part_change_string_group_string_group_string PARTITION(part=1 POSTHOOK: Lineage: part_change_string_group_string_group_string PARTITION(part=1).c9 EXPRESSION [(schema_evolution_data)schema_evolution_data.FieldSchema(name:string2, type:string, comment:null), ] POSTHOOK: Lineage: part_change_string_group_string_group_string PARTITION(part=1).insert_num SIMPLE [(schema_evolution_data)schema_evolution_data.FieldSchema(name:insert_num, type:int, comment:null), ] _col0 _col1 _col2 _col3 _col4 _col5 _col6 _col7 _col8 _col9 _col10 _col11 +PREHOOK: query: explain vectorization only detail +select insert_num,part,c1,c2,c3,c4,b from part_change_string_group_string_group_string +PREHOOK: type: QUERY +POSTHOOK: query: explain vectorization only detail +select insert_num,part,c1,c2,c3,c4,b from part_change_string_group_string_group_string +POSTHOOK: type: QUERY +Explain +PLAN VECTORIZATION: + enabled: true + enabledConditionsMet: [hive.vectorized.execution.enabled IS true] + +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez + Vertices: + Map 1 + Map Operator Tree: + TableScan Vectorization: + native: true + projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12] + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumns: [0, 12, 1, 2, 3, 4, 11] + File Sink Vectorization: + className: VectorFileSinkOperator + native: false + Execution mode: vectorized, llap + Map Vectorization: + enabled: true + enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true + groupByVectorOutput: true + inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + allNative: false + usesVectorUDFAdaptor: false + vectorized: true + rowBatchContext: + dataColumnCount: 12 + includeColumns: [0, 1, 2, 3, 4, 11] + dataColumns: insert_num:int, c1:string, c2:string, c3:string, c4:string, c5:char(50), c6:char(50), c7:char(50), c8:varchar(50), c9:varchar(50), c10:varchar(50), b:string + partitionColumnCount: 1 + partitionColumns: part:int + + Stage: Stage-0 + Fetch Operator + PREHOOK: query: select insert_num,part,c1,c2,c3,c4,b from part_change_string_group_string_group_string PREHOOK: type: QUERY PREHOOK: Input: default@part_change_string_group_string_group_string @@ -854,6 +1224,56 @@ POSTHOOK: Lineage: part_change_string_group_string_group_string PARTITION(part=1 POSTHOOK: Lineage: part_change_string_group_string_group_string PARTITION(part=1).c9 EXPRESSION [(values__tmp__table__8)values__tmp__table__8.FieldSchema(name:tmp_values_col10, type:string, comment:), ] POSTHOOK: Lineage: part_change_string_group_string_group_string PARTITION(part=1).insert_num EXPRESSION [(values__tmp__table__8)values__tmp__table__8.FieldSchema(name:tmp_values_col1, type:string, comment:), ] _col0 _col1 _col2 _col3 _col4 _col5 _col6 _col7 _col8 _col9 _col10 _col11 +PREHOOK: query: explain vectorization only detail +select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,b from part_change_string_group_string_group_string +PREHOOK: type: QUERY +POSTHOOK: query: explain vectorization only detail +select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,b from part_change_string_group_string_group_string +POSTHOOK: type: QUERY +Explain +PLAN VECTORIZATION: + enabled: true + enabledConditionsMet: [hive.vectorized.execution.enabled IS true] + +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez + Vertices: + Map 1 + Map Operator Tree: + TableScan Vectorization: + native: true + projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12] + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumns: [0, 12, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11] + File Sink Vectorization: + className: VectorFileSinkOperator + native: false + Execution mode: vectorized, llap + Map Vectorization: + enabled: true + enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true + groupByVectorOutput: true + inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + allNative: false + usesVectorUDFAdaptor: false + vectorized: true + rowBatchContext: + dataColumnCount: 12 + includeColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11] + dataColumns: insert_num:int, c1:char(50), c2:char(9), c3:varchar(50), c4:char(9), c5:varchar(50), c6:varchar(9), c7:string, c8:char(50), c9:char(9), c10:string, b:string + partitionColumnCount: 1 + partitionColumns: part:int + + Stage: Stage-0 + Fetch Operator + PREHOOK: query: select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,b from part_change_string_group_string_group_string PREHOOK: type: QUERY PREHOOK: Input: default@part_change_string_group_string_group_string @@ -936,6 +1356,56 @@ POSTHOOK: Lineage: part_change_lower_to_higher_numeric_group_tinyint_to_bigint P POSTHOOK: Lineage: part_change_lower_to_higher_numeric_group_tinyint_to_bigint PARTITION(part=1).c9 SIMPLE [(schema_evolution_data)schema_evolution_data.FieldSchema(name:smallint1, type:smallint, comment:null), ] POSTHOOK: Lineage: part_change_lower_to_higher_numeric_group_tinyint_to_bigint PARTITION(part=1).insert_num SIMPLE [(schema_evolution_data)schema_evolution_data.FieldSchema(name:insert_num, type:int, comment:null), ] insert_num tinyint1 tinyint1 tinyint1 tinyint1 tinyint1 tinyint1 smallint1 smallint1 smallint1 smallint1 smallint1 int1 int1 int1 int1 bigint1 bigint1 bigint1 _c19 +PREHOOK: query: explain vectorization only detail +select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,c16,c17,c18,b from part_change_lower_to_higher_numeric_group_tinyint_to_bigint +PREHOOK: type: QUERY +POSTHOOK: query: explain vectorization only detail +select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,c16,c17,c18,b from part_change_lower_to_higher_numeric_group_tinyint_to_bigint +POSTHOOK: type: QUERY +Explain +PLAN VECTORIZATION: + enabled: true + enabledConditionsMet: [hive.vectorized.execution.enabled IS true] + +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez + Vertices: + Map 1 + Map Operator Tree: + TableScan Vectorization: + native: true + projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20] + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumns: [0, 20, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19] + File Sink Vectorization: + className: VectorFileSinkOperator + native: false + Execution mode: vectorized, llap + Map Vectorization: + enabled: true + enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true + groupByVectorOutput: true + inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + allNative: false + usesVectorUDFAdaptor: false + vectorized: true + rowBatchContext: + dataColumnCount: 20 + includeColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19] + dataColumns: insert_num:int, c1:tinyint, c2:tinyint, c3:tinyint, c4:tinyint, c5:tinyint, c6:tinyint, c7:smallint, c8:smallint, c9:smallint, c10:smallint, c11:smallint, c12:int, c13:int, c14:int, c15:int, c16:bigint, c17:bigint, c18:bigint, b:string + partitionColumnCount: 1 + partitionColumns: part:int + + Stage: Stage-0 + Fetch Operator + PREHOOK: query: select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,c16,c17,c18,b from part_change_lower_to_higher_numeric_group_tinyint_to_bigint PREHOOK: type: QUERY PREHOOK: Input: default@part_change_lower_to_higher_numeric_group_tinyint_to_bigint @@ -1007,6 +1477,56 @@ POSTHOOK: Lineage: part_change_lower_to_higher_numeric_group_tinyint_to_bigint P POSTHOOK: Lineage: part_change_lower_to_higher_numeric_group_tinyint_to_bigint PARTITION(part=1).c9 EXPRESSION [(values__tmp__table__9)values__tmp__table__9.FieldSchema(name:tmp_values_col10, type:string, comment:), ] POSTHOOK: Lineage: part_change_lower_to_higher_numeric_group_tinyint_to_bigint PARTITION(part=1).insert_num EXPRESSION [(values__tmp__table__9)values__tmp__table__9.FieldSchema(name:tmp_values_col1, type:string, comment:), ] _col0 _col1 _col2 _col3 _col4 _col5 _col6 _col7 _col8 _col9 _col10 _col11 _col12 _col13 _col14 _col15 _col16 _col17 _col18 _col19 +PREHOOK: query: explain vectorization only detail +select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,c16,c17,c18,b from part_change_lower_to_higher_numeric_group_tinyint_to_bigint +PREHOOK: type: QUERY +POSTHOOK: query: explain vectorization only detail +select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,c16,c17,c18,b from part_change_lower_to_higher_numeric_group_tinyint_to_bigint +POSTHOOK: type: QUERY +Explain +PLAN VECTORIZATION: + enabled: true + enabledConditionsMet: [hive.vectorized.execution.enabled IS true] + +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez + Vertices: + Map 1 + Map Operator Tree: + TableScan Vectorization: + native: true + projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20] + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumns: [0, 20, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19] + File Sink Vectorization: + className: VectorFileSinkOperator + native: false + Execution mode: vectorized, llap + Map Vectorization: + enabled: true + enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true + groupByVectorOutput: true + inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + allNative: false + usesVectorUDFAdaptor: false + vectorized: true + rowBatchContext: + dataColumnCount: 20 + includeColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19] + dataColumns: insert_num:int, c1:smallint, c2:int, c3:bigint, c4:decimal(38,18), c5:float, c6:double, c7:int, c8:bigint, c9:decimal(38,18), c10:float, c11:double, c12:bigint, c13:decimal(38,18), c14:float, c15:double, c16:decimal(38,18), c17:float, c18:double, b:string + partitionColumnCount: 1 + partitionColumns: part:int + + Stage: Stage-0 + Fetch Operator + PREHOOK: query: select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,c16,c17,c18,b from part_change_lower_to_higher_numeric_group_tinyint_to_bigint PREHOOK: type: QUERY PREHOOK: Input: default@part_change_lower_to_higher_numeric_group_tinyint_to_bigint @@ -1066,6 +1586,56 @@ POSTHOOK: Lineage: part_change_lower_to_higher_numeric_group_decimal_to_float PA POSTHOOK: Lineage: part_change_lower_to_higher_numeric_group_decimal_to_float PARTITION(part=1).c3 SIMPLE [(schema_evolution_data)schema_evolution_data.FieldSchema(name:float1, type:float, comment:null), ] POSTHOOK: Lineage: part_change_lower_to_higher_numeric_group_decimal_to_float PARTITION(part=1).insert_num SIMPLE [(schema_evolution_data)schema_evolution_data.FieldSchema(name:insert_num, type:int, comment:null), ] insert_num decimal1 decimal1 float1 _c4 +PREHOOK: query: explain vectorization only detail +select insert_num,part,c1,c2,c3,b from part_change_lower_to_higher_numeric_group_decimal_to_float +PREHOOK: type: QUERY +POSTHOOK: query: explain vectorization only detail +select insert_num,part,c1,c2,c3,b from part_change_lower_to_higher_numeric_group_decimal_to_float +POSTHOOK: type: QUERY +Explain +PLAN VECTORIZATION: + enabled: true + enabledConditionsMet: [hive.vectorized.execution.enabled IS true] + +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez + Vertices: + Map 1 + Map Operator Tree: + TableScan Vectorization: + native: true + projectedOutputColumns: [0, 1, 2, 3, 4, 5] + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumns: [0, 5, 1, 2, 3, 4] + File Sink Vectorization: + className: VectorFileSinkOperator + native: false + Execution mode: vectorized, llap + Map Vectorization: + enabled: true + enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true + groupByVectorOutput: true + inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + allNative: false + usesVectorUDFAdaptor: false + vectorized: true + rowBatchContext: + dataColumnCount: 5 + includeColumns: [0, 1, 2, 3, 4] + dataColumns: insert_num:int, c1:decimal(38,18), c2:decimal(38,18), c3:float, b:string + partitionColumnCount: 1 + partitionColumns: part:int + + Stage: Stage-0 + Fetch Operator + PREHOOK: query: select insert_num,part,c1,c2,c3,b from part_change_lower_to_higher_numeric_group_decimal_to_float PREHOOK: type: QUERY PREHOOK: Input: default@part_change_lower_to_higher_numeric_group_decimal_to_float @@ -1102,6 +1672,56 @@ POSTHOOK: Lineage: part_change_lower_to_higher_numeric_group_decimal_to_float PA POSTHOOK: Lineage: part_change_lower_to_higher_numeric_group_decimal_to_float PARTITION(part=1).c3 EXPRESSION [(values__tmp__table__10)values__tmp__table__10.FieldSchema(name:tmp_values_col4, type:string, comment:), ] POSTHOOK: Lineage: part_change_lower_to_higher_numeric_group_decimal_to_float PARTITION(part=1).insert_num EXPRESSION [(values__tmp__table__10)values__tmp__table__10.FieldSchema(name:tmp_values_col1, type:string, comment:), ] _col0 _col1 _col2 _col3 _col4 +PREHOOK: query: explain vectorization only detail +select insert_num,part,c1,c2,c3,b from part_change_lower_to_higher_numeric_group_decimal_to_float +PREHOOK: type: QUERY +POSTHOOK: query: explain vectorization only detail +select insert_num,part,c1,c2,c3,b from part_change_lower_to_higher_numeric_group_decimal_to_float +POSTHOOK: type: QUERY +Explain +PLAN VECTORIZATION: + enabled: true + enabledConditionsMet: [hive.vectorized.execution.enabled IS true] + +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez + Vertices: + Map 1 + Map Operator Tree: + TableScan Vectorization: + native: true + projectedOutputColumns: [0, 1, 2, 3, 4, 5] + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumns: [0, 5, 1, 2, 3, 4] + File Sink Vectorization: + className: VectorFileSinkOperator + native: false + Execution mode: vectorized, llap + Map Vectorization: + enabled: true + enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true + groupByVectorOutput: true + inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + allNative: false + usesVectorUDFAdaptor: false + vectorized: true + rowBatchContext: + dataColumnCount: 5 + includeColumns: [0, 1, 2, 3, 4] + dataColumns: insert_num:int, c1:float, c2:double, c3:double, b:string + partitionColumnCount: 1 + partitionColumns: part:int + + Stage: Stage-0 + Fetch Operator + PREHOOK: query: select insert_num,part,c1,c2,c3,b from part_change_lower_to_higher_numeric_group_decimal_to_float PREHOOK: type: QUERY PREHOOK: Input: default@part_change_lower_to_higher_numeric_group_decimal_to_float diff --git ql/src/test/results/clientpositive/llap/schema_evol_orc_acidvec_table.q.out ql/src/test/results/clientpositive/llap/schema_evol_orc_acidvec_table.q.out index ce33ed0..5e08bb4 100644 --- ql/src/test/results/clientpositive/llap/schema_evol_orc_acidvec_table.q.out +++ ql/src/test/results/clientpositive/llap/schema_evol_orc_acidvec_table.q.out @@ -55,6 +55,55 @@ POSTHOOK: Lineage: table_add_int_permute_select.b SIMPLE [(values__tmp__table__1 POSTHOOK: Lineage: table_add_int_permute_select.c EXPRESSION [(values__tmp__table__1)values__tmp__table__1.FieldSchema(name:tmp_values_col4, type:string, comment:), ] POSTHOOK: Lineage: table_add_int_permute_select.insert_num EXPRESSION [(values__tmp__table__1)values__tmp__table__1.FieldSchema(name:tmp_values_col1, type:string, comment:), ] _col0 _col1 _col2 _col3 +PREHOOK: query: explain vectorization only detail +select insert_num,a,b,c from table_add_int_permute_select +PREHOOK: type: QUERY +POSTHOOK: query: explain vectorization only detail +select insert_num,a,b,c from table_add_int_permute_select +POSTHOOK: type: QUERY +Explain +PLAN VECTORIZATION: + enabled: true + enabledConditionsMet: [hive.vectorized.execution.enabled IS true] + +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez + Vertices: + Map 1 + Map Operator Tree: + TableScan Vectorization: + native: true + projectedOutputColumns: [0, 1, 2, 3] + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumns: [0, 1, 2, 3] + File Sink Vectorization: + className: VectorFileSinkOperator + native: false + Execution mode: vectorized, llap + Map Vectorization: + enabled: true + enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true + groupByVectorOutput: true + inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + allNative: false + usesVectorUDFAdaptor: false + vectorized: true + rowBatchContext: + dataColumnCount: 4 + includeColumns: [0, 1, 2, 3] + dataColumns: insert_num:int, a:int, b:string, c:int + partitionColumnCount: 0 + + Stage: Stage-0 + Fetch Operator + PREHOOK: query: select insert_num,a,b from table_add_int_permute_select PREHOOK: type: QUERY PREHOOK: Input: default@table_add_int_permute_select @@ -148,6 +197,55 @@ POSTHOOK: Lineage: table_add_int_string_permute_select.c EXPRESSION [(values__tm POSTHOOK: Lineage: table_add_int_string_permute_select.d SIMPLE [(values__tmp__table__2)values__tmp__table__2.FieldSchema(name:tmp_values_col5, type:string, comment:), ] POSTHOOK: Lineage: table_add_int_string_permute_select.insert_num EXPRESSION [(values__tmp__table__2)values__tmp__table__2.FieldSchema(name:tmp_values_col1, type:string, comment:), ] _col0 _col1 _col2 _col3 _col4 +PREHOOK: query: explain vectorization only detail +select insert_num,a,b,c,d from table_add_int_string_permute_select +PREHOOK: type: QUERY +POSTHOOK: query: explain vectorization only detail +select insert_num,a,b,c,d from table_add_int_string_permute_select +POSTHOOK: type: QUERY +Explain +PLAN VECTORIZATION: + enabled: true + enabledConditionsMet: [hive.vectorized.execution.enabled IS true] + +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez + Vertices: + Map 1 + Map Operator Tree: + TableScan Vectorization: + native: true + projectedOutputColumns: [0, 1, 2, 3, 4] + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumns: [0, 1, 2, 3, 4] + File Sink Vectorization: + className: VectorFileSinkOperator + native: false + Execution mode: vectorized, llap + Map Vectorization: + enabled: true + enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true + groupByVectorOutput: true + inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + allNative: false + usesVectorUDFAdaptor: false + vectorized: true + rowBatchContext: + dataColumnCount: 5 + includeColumns: [0, 1, 2, 3, 4] + dataColumns: insert_num:int, a:int, b:string, c:int, d:string + partitionColumnCount: 0 + + Stage: Stage-0 + Fetch Operator + PREHOOK: query: select insert_num,a,b from table_add_int_string_permute_select PREHOOK: type: QUERY PREHOOK: Input: default@table_add_int_string_permute_select @@ -303,6 +401,55 @@ POSTHOOK: Lineage: table_change_string_group_double.c2 EXPRESSION [(values__tmp_ POSTHOOK: Lineage: table_change_string_group_double.c3 EXPRESSION [(values__tmp__table__3)values__tmp__table__3.FieldSchema(name:tmp_values_col4, type:string, comment:), ] POSTHOOK: Lineage: table_change_string_group_double.insert_num EXPRESSION [(values__tmp__table__3)values__tmp__table__3.FieldSchema(name:tmp_values_col1, type:string, comment:), ] _col0 _col1 _col2 _col3 _col4 +PREHOOK: query: explain vectorization only detail +select insert_num,c1,c2,c3,b from table_change_string_group_double +PREHOOK: type: QUERY +POSTHOOK: query: explain vectorization only detail +select insert_num,c1,c2,c3,b from table_change_string_group_double +POSTHOOK: type: QUERY +Explain +PLAN VECTORIZATION: + enabled: true + enabledConditionsMet: [hive.vectorized.execution.enabled IS true] + +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez + Vertices: + Map 1 + Map Operator Tree: + TableScan Vectorization: + native: true + projectedOutputColumns: [0, 1, 2, 3, 4] + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumns: [0, 1, 2, 3, 4] + File Sink Vectorization: + className: VectorFileSinkOperator + native: false + Execution mode: vectorized, llap + Map Vectorization: + enabled: true + enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true + groupByVectorOutput: true + inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + allNative: false + usesVectorUDFAdaptor: false + vectorized: true + rowBatchContext: + dataColumnCount: 5 + includeColumns: [0, 1, 2, 3, 4] + dataColumns: insert_num:int, c1:double, c2:double, c3:double, b:string + partitionColumnCount: 0 + + Stage: Stage-0 + Fetch Operator + PREHOOK: query: select insert_num,c1,c2,c3,b from table_change_string_group_double PREHOOK: type: QUERY PREHOOK: Input: default@table_change_string_group_double @@ -382,6 +529,55 @@ POSTHOOK: Lineage: table_change_date_group_string_group_date_group.c8 EXPRESSION POSTHOOK: Lineage: table_change_date_group_string_group_date_group.c9 EXPRESSION [(values__tmp__table__4)values__tmp__table__4.FieldSchema(name:tmp_values_col10, type:string, comment:), ] POSTHOOK: Lineage: table_change_date_group_string_group_date_group.insert_num EXPRESSION [(values__tmp__table__4)values__tmp__table__4.FieldSchema(name:tmp_values_col1, type:string, comment:), ] _col0 _col1 _col2 _col3 _col4 _col5 _col6 _col7 _col8 _col9 _col10 _col11 +PREHOOK: query: explain vectorization only detail +select insert_num,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,b from table_change_date_group_string_group_date_group +PREHOOK: type: QUERY +POSTHOOK: query: explain vectorization only detail +select insert_num,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,b from table_change_date_group_string_group_date_group +POSTHOOK: type: QUERY +Explain +PLAN VECTORIZATION: + enabled: true + enabledConditionsMet: [hive.vectorized.execution.enabled IS true] + +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez + Vertices: + Map 1 + Map Operator Tree: + TableScan Vectorization: + native: true + projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11] + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11] + File Sink Vectorization: + className: VectorFileSinkOperator + native: false + Execution mode: vectorized, llap + Map Vectorization: + enabled: true + enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true + groupByVectorOutput: true + inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + allNative: false + usesVectorUDFAdaptor: false + vectorized: true + rowBatchContext: + dataColumnCount: 12 + includeColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11] + dataColumns: insert_num:int, c1:string, c2:char(50), c3:char(15), c4:varchar(50), c5:varchar(15), c6:string, c7:char(50), c8:char(15), c9:varchar(50), c10:varchar(15), b:string + partitionColumnCount: 0 + + Stage: Stage-0 + Fetch Operator + PREHOOK: query: select insert_num,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,b from table_change_date_group_string_group_date_group PREHOOK: type: QUERY PREHOOK: Input: default@table_change_date_group_string_group_date_group @@ -460,6 +656,55 @@ POSTHOOK: Lineage: table_change_numeric_group_string_group_multi_ints_string_gro POSTHOOK: Lineage: table_change_numeric_group_string_group_multi_ints_string_group.c9 SIMPLE [(schema_evolution_data)schema_evolution_data.FieldSchema(name:tinyint1, type:tinyint, comment:null), ] POSTHOOK: Lineage: table_change_numeric_group_string_group_multi_ints_string_group.insert_num SIMPLE [(schema_evolution_data)schema_evolution_data.FieldSchema(name:insert_num, type:int, comment:null), ] insert_num tinyint1 smallint1 int1 bigint1 tinyint1 smallint1 int1 bigint1 tinyint1 smallint1 int1 bigint1 tinyint1 smallint1 int1 bigint1 tinyint1 smallint1 int1 bigint1 _c21 +PREHOOK: query: explain vectorization only detail +select insert_num,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,c16,c17,c18,c19,c20,b from table_change_numeric_group_string_group_multi_ints_string_group +PREHOOK: type: QUERY +POSTHOOK: query: explain vectorization only detail +select insert_num,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,c16,c17,c18,c19,c20,b from table_change_numeric_group_string_group_multi_ints_string_group +POSTHOOK: type: QUERY +Explain +PLAN VECTORIZATION: + enabled: true + enabledConditionsMet: [hive.vectorized.execution.enabled IS true] + +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez + Vertices: + Map 1 + Map Operator Tree: + TableScan Vectorization: + native: true + projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21] + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21] + File Sink Vectorization: + className: VectorFileSinkOperator + native: false + Execution mode: vectorized, llap + Map Vectorization: + enabled: true + enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true + groupByVectorOutput: true + inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + allNative: false + usesVectorUDFAdaptor: false + vectorized: true + rowBatchContext: + dataColumnCount: 22 + includeColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21] + dataColumns: insert_num:int, c1:tinyint, c2:smallint, c3:int, c4:bigint, c5:tinyint, c6:smallint, c7:int, c8:bigint, c9:tinyint, c10:smallint, c11:int, c12:bigint, c13:tinyint, c14:smallint, c15:int, c16:bigint, c17:tinyint, c18:smallint, c19:int, c20:bigint, b:string + partitionColumnCount: 0 + + Stage: Stage-0 + Fetch Operator + PREHOOK: query: select insert_num,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,c16,c17,c18,c19,c20,b from table_change_numeric_group_string_group_multi_ints_string_group PREHOOK: type: QUERY PREHOOK: Input: default@table_change_numeric_group_string_group_multi_ints_string_group @@ -527,6 +772,55 @@ POSTHOOK: Lineage: table_change_numeric_group_string_group_multi_ints_string_gro POSTHOOK: Lineage: table_change_numeric_group_string_group_multi_ints_string_group.c9 EXPRESSION [(values__tmp__table__5)values__tmp__table__5.FieldSchema(name:tmp_values_col10, type:string, comment:), ] POSTHOOK: Lineage: table_change_numeric_group_string_group_multi_ints_string_group.insert_num EXPRESSION [(values__tmp__table__5)values__tmp__table__5.FieldSchema(name:tmp_values_col1, type:string, comment:), ] _col0 _col1 _col2 _col3 _col4 _col5 _col6 _col7 _col8 _col9 _col10 _col11 _col12 _col13 _col14 _col15 _col16 _col17 _col18 _col19 _col20 _col21 +PREHOOK: query: explain vectorization only detail +select insert_num,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,c16,c17,c18,c19,c20,b from table_change_numeric_group_string_group_multi_ints_string_group +PREHOOK: type: QUERY +POSTHOOK: query: explain vectorization only detail +select insert_num,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,c16,c17,c18,c19,c20,b from table_change_numeric_group_string_group_multi_ints_string_group +POSTHOOK: type: QUERY +Explain +PLAN VECTORIZATION: + enabled: true + enabledConditionsMet: [hive.vectorized.execution.enabled IS true] + +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez + Vertices: + Map 1 + Map Operator Tree: + TableScan Vectorization: + native: true + projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21] + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21] + File Sink Vectorization: + className: VectorFileSinkOperator + native: false + Execution mode: vectorized, llap + Map Vectorization: + enabled: true + enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true + groupByVectorOutput: true + inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + allNative: false + usesVectorUDFAdaptor: false + vectorized: true + rowBatchContext: + dataColumnCount: 22 + includeColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21] + dataColumns: insert_num:int, c1:string, c2:string, c3:string, c4:string, c5:char(50), c6:char(50), c7:char(50), c8:char(50), c9:char(5), c10:char(5), c11:char(5), c12:char(5), c13:varchar(50), c14:varchar(50), c15:varchar(50), c16:varchar(50), c17:varchar(5), c18:varchar(5), c19:varchar(5), c20:varchar(5), b:string + partitionColumnCount: 0 + + Stage: Stage-0 + Fetch Operator + PREHOOK: query: select insert_num,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,c16,c17,c18,c19,c20,b from table_change_numeric_group_string_group_multi_ints_string_group PREHOOK: type: QUERY PREHOOK: Input: default@table_change_numeric_group_string_group_multi_ints_string_group @@ -600,6 +894,55 @@ POSTHOOK: Lineage: table_change_numeric_group_string_group_floating_string_group POSTHOOK: Lineage: table_change_numeric_group_string_group_floating_string_group.c9 SIMPLE [(schema_evolution_data)schema_evolution_data.FieldSchema(name:double1, type:double, comment:null), ] POSTHOOK: Lineage: table_change_numeric_group_string_group_floating_string_group.insert_num SIMPLE [(schema_evolution_data)schema_evolution_data.FieldSchema(name:insert_num, type:int, comment:null), ] insert_num decimal1 float1 double1 decimal1 float1 double1 decimal1 float1 double1 decimal1 float1 double1 decimal1 float1 double1 _c16 +PREHOOK: query: explain vectorization only detail +select insert_num,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,b from table_change_numeric_group_string_group_floating_string_group +PREHOOK: type: QUERY +POSTHOOK: query: explain vectorization only detail +select insert_num,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,b from table_change_numeric_group_string_group_floating_string_group +POSTHOOK: type: QUERY +Explain +PLAN VECTORIZATION: + enabled: true + enabledConditionsMet: [hive.vectorized.execution.enabled IS true] + +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez + Vertices: + Map 1 + Map Operator Tree: + TableScan Vectorization: + native: true + projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16] + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16] + File Sink Vectorization: + className: VectorFileSinkOperator + native: false + Execution mode: vectorized, llap + Map Vectorization: + enabled: true + enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true + groupByVectorOutput: true + inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + allNative: false + usesVectorUDFAdaptor: false + vectorized: true + rowBatchContext: + dataColumnCount: 17 + includeColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16] + dataColumns: insert_num:int, c1:decimal(38,18), c2:float, c3:double, c4:decimal(38,18), c5:float, c6:double, c7:decimal(38,18), c8:float, c9:double, c10:decimal(38,18), c11:float, c12:double, c13:decimal(38,18), c14:float, c15:double, b:string + partitionColumnCount: 0 + + Stage: Stage-0 + Fetch Operator + PREHOOK: query: select insert_num,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,b from table_change_numeric_group_string_group_floating_string_group PREHOOK: type: QUERY PREHOOK: Input: default@table_change_numeric_group_string_group_floating_string_group @@ -662,6 +1005,55 @@ POSTHOOK: Lineage: table_change_numeric_group_string_group_floating_string_group POSTHOOK: Lineage: table_change_numeric_group_string_group_floating_string_group.c9 EXPRESSION [(values__tmp__table__6)values__tmp__table__6.FieldSchema(name:tmp_values_col10, type:string, comment:), ] POSTHOOK: Lineage: table_change_numeric_group_string_group_floating_string_group.insert_num EXPRESSION [(values__tmp__table__6)values__tmp__table__6.FieldSchema(name:tmp_values_col1, type:string, comment:), ] _col0 _col1 _col2 _col3 _col4 _col5 _col6 _col7 _col8 _col9 _col10 _col11 _col12 _col13 _col14 _col15 _col16 +PREHOOK: query: explain vectorization only detail +select insert_num,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,b from table_change_numeric_group_string_group_floating_string_group +PREHOOK: type: QUERY +POSTHOOK: query: explain vectorization only detail +select insert_num,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,b from table_change_numeric_group_string_group_floating_string_group +POSTHOOK: type: QUERY +Explain +PLAN VECTORIZATION: + enabled: true + enabledConditionsMet: [hive.vectorized.execution.enabled IS true] + +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez + Vertices: + Map 1 + Map Operator Tree: + TableScan Vectorization: + native: true + projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16] + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16] + File Sink Vectorization: + className: VectorFileSinkOperator + native: false + Execution mode: vectorized, llap + Map Vectorization: + enabled: true + enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true + groupByVectorOutput: true + inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + allNative: false + usesVectorUDFAdaptor: false + vectorized: true + rowBatchContext: + dataColumnCount: 17 + includeColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16] + dataColumns: insert_num:int, c1:string, c2:string, c3:string, c4:char(50), c5:char(50), c6:char(50), c7:char(7), c8:char(7), c9:char(7), c10:varchar(50), c11:varchar(50), c12:varchar(50), c13:varchar(7), c14:varchar(7), c15:varchar(7), b:string + partitionColumnCount: 0 + + Stage: Stage-0 + Fetch Operator + PREHOOK: query: select insert_num,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,b from table_change_numeric_group_string_group_floating_string_group PREHOOK: type: QUERY PREHOOK: Input: default@table_change_numeric_group_string_group_floating_string_group @@ -728,6 +1120,55 @@ POSTHOOK: Lineage: table_change_string_group_string_group_string.c8 EXPRESSION [ POSTHOOK: Lineage: table_change_string_group_string_group_string.c9 EXPRESSION [(schema_evolution_data)schema_evolution_data.FieldSchema(name:string2, type:string, comment:null), ] POSTHOOK: Lineage: table_change_string_group_string_group_string.insert_num SIMPLE [(schema_evolution_data)schema_evolution_data.FieldSchema(name:insert_num, type:int, comment:null), ] _col0 _col1 _col2 _col3 _col4 _col5 _col6 _col7 _col8 _col9 _col10 _col11 +PREHOOK: query: explain vectorization only detail +select insert_num,c1,c2,c3,c4,b from table_change_string_group_string_group_string +PREHOOK: type: QUERY +POSTHOOK: query: explain vectorization only detail +select insert_num,c1,c2,c3,c4,b from table_change_string_group_string_group_string +POSTHOOK: type: QUERY +Explain +PLAN VECTORIZATION: + enabled: true + enabledConditionsMet: [hive.vectorized.execution.enabled IS true] + +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez + Vertices: + Map 1 + Map Operator Tree: + TableScan Vectorization: + native: true + projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11] + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumns: [0, 1, 2, 3, 4, 11] + File Sink Vectorization: + className: VectorFileSinkOperator + native: false + Execution mode: vectorized, llap + Map Vectorization: + enabled: true + enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true + groupByVectorOutput: true + inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + allNative: false + usesVectorUDFAdaptor: false + vectorized: true + rowBatchContext: + dataColumnCount: 12 + includeColumns: [0, 1, 2, 3, 4, 11] + dataColumns: insert_num:int, c1:string, c2:string, c3:string, c4:string, c5:char(50), c6:char(50), c7:char(50), c8:varchar(50), c9:varchar(50), c10:varchar(50), b:string + partitionColumnCount: 0 + + Stage: Stage-0 + Fetch Operator + PREHOOK: query: select insert_num,c1,c2,c3,c4,b from table_change_string_group_string_group_string PREHOOK: type: QUERY PREHOOK: Input: default@table_change_string_group_string_group_string @@ -783,6 +1224,55 @@ POSTHOOK: Lineage: table_change_string_group_string_group_string.c8 EXPRESSION [ POSTHOOK: Lineage: table_change_string_group_string_group_string.c9 EXPRESSION [(values__tmp__table__7)values__tmp__table__7.FieldSchema(name:tmp_values_col10, type:string, comment:), ] POSTHOOK: Lineage: table_change_string_group_string_group_string.insert_num EXPRESSION [(values__tmp__table__7)values__tmp__table__7.FieldSchema(name:tmp_values_col1, type:string, comment:), ] _col0 _col1 _col2 _col3 _col4 _col5 _col6 _col7 _col8 _col9 _col10 _col11 +PREHOOK: query: explain vectorization only detail +select insert_num,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,b from table_change_string_group_string_group_string +PREHOOK: type: QUERY +POSTHOOK: query: explain vectorization only detail +select insert_num,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,b from table_change_string_group_string_group_string +POSTHOOK: type: QUERY +Explain +PLAN VECTORIZATION: + enabled: true + enabledConditionsMet: [hive.vectorized.execution.enabled IS true] + +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez + Vertices: + Map 1 + Map Operator Tree: + TableScan Vectorization: + native: true + projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11] + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11] + File Sink Vectorization: + className: VectorFileSinkOperator + native: false + Execution mode: vectorized, llap + Map Vectorization: + enabled: true + enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true + groupByVectorOutput: true + inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + allNative: false + usesVectorUDFAdaptor: false + vectorized: true + rowBatchContext: + dataColumnCount: 12 + includeColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11] + dataColumns: insert_num:int, c1:char(50), c2:char(9), c3:varchar(50), c4:char(9), c5:varchar(50), c6:varchar(9), c7:string, c8:char(50), c9:char(9), c10:string, b:string + partitionColumnCount: 0 + + Stage: Stage-0 + Fetch Operator + PREHOOK: query: select insert_num,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,b from table_change_string_group_string_group_string PREHOOK: type: QUERY PREHOOK: Input: default@table_change_string_group_string_group_string @@ -863,6 +1353,55 @@ POSTHOOK: Lineage: table_change_lower_to_higher_numeric_group_tinyint_to_bigint. POSTHOOK: Lineage: table_change_lower_to_higher_numeric_group_tinyint_to_bigint.c9 SIMPLE [(schema_evolution_data)schema_evolution_data.FieldSchema(name:smallint1, type:smallint, comment:null), ] POSTHOOK: Lineage: table_change_lower_to_higher_numeric_group_tinyint_to_bigint.insert_num SIMPLE [(schema_evolution_data)schema_evolution_data.FieldSchema(name:insert_num, type:int, comment:null), ] insert_num tinyint1 tinyint1 tinyint1 tinyint1 tinyint1 tinyint1 smallint1 smallint1 smallint1 smallint1 smallint1 int1 int1 int1 int1 bigint1 bigint1 bigint1 _c19 +PREHOOK: query: explain vectorization only detail +select insert_num,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,c16,c17,c18,b from table_change_lower_to_higher_numeric_group_tinyint_to_bigint +PREHOOK: type: QUERY +POSTHOOK: query: explain vectorization only detail +select insert_num,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,c16,c17,c18,b from table_change_lower_to_higher_numeric_group_tinyint_to_bigint +POSTHOOK: type: QUERY +Explain +PLAN VECTORIZATION: + enabled: true + enabledConditionsMet: [hive.vectorized.execution.enabled IS true] + +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez + Vertices: + Map 1 + Map Operator Tree: + TableScan Vectorization: + native: true + projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19] + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19] + File Sink Vectorization: + className: VectorFileSinkOperator + native: false + Execution mode: vectorized, llap + Map Vectorization: + enabled: true + enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true + groupByVectorOutput: true + inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + allNative: false + usesVectorUDFAdaptor: false + vectorized: true + rowBatchContext: + dataColumnCount: 20 + includeColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19] + dataColumns: insert_num:int, c1:tinyint, c2:tinyint, c3:tinyint, c4:tinyint, c5:tinyint, c6:tinyint, c7:smallint, c8:smallint, c9:smallint, c10:smallint, c11:smallint, c12:int, c13:int, c14:int, c15:int, c16:bigint, c17:bigint, c18:bigint, b:string + partitionColumnCount: 0 + + Stage: Stage-0 + Fetch Operator + PREHOOK: query: select insert_num,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,c16,c17,c18,b from table_change_lower_to_higher_numeric_group_tinyint_to_bigint PREHOOK: type: QUERY PREHOOK: Input: default@table_change_lower_to_higher_numeric_group_tinyint_to_bigint @@ -932,6 +1471,55 @@ POSTHOOK: Lineage: table_change_lower_to_higher_numeric_group_tinyint_to_bigint. POSTHOOK: Lineage: table_change_lower_to_higher_numeric_group_tinyint_to_bigint.c9 EXPRESSION [(values__tmp__table__8)values__tmp__table__8.FieldSchema(name:tmp_values_col10, type:string, comment:), ] POSTHOOK: Lineage: table_change_lower_to_higher_numeric_group_tinyint_to_bigint.insert_num EXPRESSION [(values__tmp__table__8)values__tmp__table__8.FieldSchema(name:tmp_values_col1, type:string, comment:), ] _col0 _col1 _col2 _col3 _col4 _col5 _col6 _col7 _col8 _col9 _col10 _col11 _col12 _col13 _col14 _col15 _col16 _col17 _col18 _col19 +PREHOOK: query: explain vectorization only detail +select insert_num,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,c16,c17,c18,b from table_change_lower_to_higher_numeric_group_tinyint_to_bigint +PREHOOK: type: QUERY +POSTHOOK: query: explain vectorization only detail +select insert_num,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,c16,c17,c18,b from table_change_lower_to_higher_numeric_group_tinyint_to_bigint +POSTHOOK: type: QUERY +Explain +PLAN VECTORIZATION: + enabled: true + enabledConditionsMet: [hive.vectorized.execution.enabled IS true] + +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez + Vertices: + Map 1 + Map Operator Tree: + TableScan Vectorization: + native: true + projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19] + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19] + File Sink Vectorization: + className: VectorFileSinkOperator + native: false + Execution mode: vectorized, llap + Map Vectorization: + enabled: true + enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true + groupByVectorOutput: true + inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + allNative: false + usesVectorUDFAdaptor: false + vectorized: true + rowBatchContext: + dataColumnCount: 20 + includeColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19] + dataColumns: insert_num:int, c1:smallint, c2:int, c3:bigint, c4:decimal(38,18), c5:float, c6:double, c7:int, c8:bigint, c9:decimal(38,18), c10:float, c11:double, c12:bigint, c13:decimal(38,18), c14:float, c15:double, c16:decimal(38,18), c17:float, c18:double, b:string + partitionColumnCount: 0 + + Stage: Stage-0 + Fetch Operator + PREHOOK: query: select insert_num,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,c16,c17,c18,b from table_change_lower_to_higher_numeric_group_tinyint_to_bigint PREHOOK: type: QUERY PREHOOK: Input: default@table_change_lower_to_higher_numeric_group_tinyint_to_bigint @@ -989,6 +1577,55 @@ POSTHOOK: Lineage: table_change_lower_to_higher_numeric_group_decimal_to_float.c POSTHOOK: Lineage: table_change_lower_to_higher_numeric_group_decimal_to_float.c3 SIMPLE [(schema_evolution_data)schema_evolution_data.FieldSchema(name:float1, type:float, comment:null), ] POSTHOOK: Lineage: table_change_lower_to_higher_numeric_group_decimal_to_float.insert_num SIMPLE [(schema_evolution_data)schema_evolution_data.FieldSchema(name:insert_num, type:int, comment:null), ] insert_num decimal1 decimal1 float1 _c4 +PREHOOK: query: explain vectorization only detail +select insert_num,c1,c2,c3,b from table_change_lower_to_higher_numeric_group_decimal_to_float +PREHOOK: type: QUERY +POSTHOOK: query: explain vectorization only detail +select insert_num,c1,c2,c3,b from table_change_lower_to_higher_numeric_group_decimal_to_float +POSTHOOK: type: QUERY +Explain +PLAN VECTORIZATION: + enabled: true + enabledConditionsMet: [hive.vectorized.execution.enabled IS true] + +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez + Vertices: + Map 1 + Map Operator Tree: + TableScan Vectorization: + native: true + projectedOutputColumns: [0, 1, 2, 3, 4] + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumns: [0, 1, 2, 3, 4] + File Sink Vectorization: + className: VectorFileSinkOperator + native: false + Execution mode: vectorized, llap + Map Vectorization: + enabled: true + enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true + groupByVectorOutput: true + inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + allNative: false + usesVectorUDFAdaptor: false + vectorized: true + rowBatchContext: + dataColumnCount: 5 + includeColumns: [0, 1, 2, 3, 4] + dataColumns: insert_num:int, c1:decimal(38,18), c2:decimal(38,18), c3:float, b:string + partitionColumnCount: 0 + + Stage: Stage-0 + Fetch Operator + PREHOOK: query: select insert_num,c1,c2,c3,b from table_change_lower_to_higher_numeric_group_decimal_to_float PREHOOK: type: QUERY PREHOOK: Input: default@table_change_lower_to_higher_numeric_group_decimal_to_float @@ -1023,6 +1660,55 @@ POSTHOOK: Lineage: table_change_lower_to_higher_numeric_group_decimal_to_float.c POSTHOOK: Lineage: table_change_lower_to_higher_numeric_group_decimal_to_float.c3 EXPRESSION [(values__tmp__table__9)values__tmp__table__9.FieldSchema(name:tmp_values_col4, type:string, comment:), ] POSTHOOK: Lineage: table_change_lower_to_higher_numeric_group_decimal_to_float.insert_num EXPRESSION [(values__tmp__table__9)values__tmp__table__9.FieldSchema(name:tmp_values_col1, type:string, comment:), ] _col0 _col1 _col2 _col3 _col4 +PREHOOK: query: explain vectorization only detail +select insert_num,c1,c2,c3,b from table_change_lower_to_higher_numeric_group_decimal_to_float +PREHOOK: type: QUERY +POSTHOOK: query: explain vectorization only detail +select insert_num,c1,c2,c3,b from table_change_lower_to_higher_numeric_group_decimal_to_float +POSTHOOK: type: QUERY +Explain +PLAN VECTORIZATION: + enabled: true + enabledConditionsMet: [hive.vectorized.execution.enabled IS true] + +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez + Vertices: + Map 1 + Map Operator Tree: + TableScan Vectorization: + native: true + projectedOutputColumns: [0, 1, 2, 3, 4] + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumns: [0, 1, 2, 3, 4] + File Sink Vectorization: + className: VectorFileSinkOperator + native: false + Execution mode: vectorized, llap + Map Vectorization: + enabled: true + enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true + groupByVectorOutput: true + inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + allNative: false + usesVectorUDFAdaptor: false + vectorized: true + rowBatchContext: + dataColumnCount: 5 + includeColumns: [0, 1, 2, 3, 4] + dataColumns: insert_num:int, c1:float, c2:double, c3:double, b:string + partitionColumnCount: 0 + + Stage: Stage-0 + Fetch Operator + PREHOOK: query: select insert_num,c1,c2,c3,b from table_change_lower_to_higher_numeric_group_decimal_to_float PREHOOK: type: QUERY PREHOOK: Input: default@table_change_lower_to_higher_numeric_group_decimal_to_float diff --git ql/src/test/results/clientpositive/llap/schema_evol_orc_nonvec_part.q.out ql/src/test/results/clientpositive/llap/schema_evol_orc_nonvec_part.q.out index cc98981..0ebb378 100644 --- ql/src/test/results/clientpositive/llap/schema_evol_orc_nonvec_part.q.out +++ ql/src/test/results/clientpositive/llap/schema_evol_orc_nonvec_part.q.out @@ -53,25 +53,49 @@ POSTHOOK: Lineage: part_add_int_permute_select PARTITION(part=1).b SIMPLE [(valu POSTHOOK: Lineage: part_add_int_permute_select PARTITION(part=1).c EXPRESSION [(values__tmp__table__2)values__tmp__table__2.FieldSchema(name:tmp_values_col4, type:string, comment:), ] POSTHOOK: Lineage: part_add_int_permute_select PARTITION(part=1).insert_num EXPRESSION [(values__tmp__table__2)values__tmp__table__2.FieldSchema(name:tmp_values_col1, type:string, comment:), ] _col0 _col1 _col2 _col3 -PREHOOK: query: explain +PREHOOK: query: explain vectorization detail select insert_num,part,a,b from part_add_int_permute_select PREHOOK: type: QUERY -POSTHOOK: query: explain +POSTHOOK: query: explain vectorization detail select insert_num,part,a,b from part_add_int_permute_select POSTHOOK: type: QUERY Explain -Plan optimized by CBO. +PLAN VECTORIZATION: + enabled: false + enabledConditionsNotMet: [hive.vectorized.execution.enabled IS false] -Stage-0 - Fetch Operator - limit:-1 - Stage-1 - Map 1 llap - File Output Operator [FS_2] - Select Operator [SEL_1] (rows=2 width=4) - Output:["_col0","_col1","_col2","_col3"] - TableScan [TS_0] (rows=2 width=101) - default@part_add_int_permute_select,part_add_int_permute_select,Tbl:COMPLETE,Col:PARTIAL,Output:["insert_num","a","b"] +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: part_add_int_permute_select + Statistics: Num rows: 2 Data size: 202 Basic stats: COMPLETE Column stats: PARTIAL + Select Operator + expressions: insert_num (type: int), part (type: int), a (type: int), b (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: PARTIAL + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: PARTIAL + 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 + Execution mode: llap + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink PREHOOK: query: select insert_num,part,a,b from part_add_int_permute_select PREHOOK: type: QUERY @@ -158,25 +182,49 @@ POSTHOOK: Lineage: part_add_int_string_permute_select PARTITION(part=1).c EXPRES POSTHOOK: Lineage: part_add_int_string_permute_select PARTITION(part=1).d SIMPLE [(values__tmp__table__4)values__tmp__table__4.FieldSchema(name:tmp_values_col5, type:string, comment:), ] POSTHOOK: Lineage: part_add_int_string_permute_select PARTITION(part=1).insert_num EXPRESSION [(values__tmp__table__4)values__tmp__table__4.FieldSchema(name:tmp_values_col1, type:string, comment:), ] _col0 _col1 _col2 _col3 _col4 -PREHOOK: query: explain +PREHOOK: query: explain vectorization detail select insert_num,part,a,b from part_add_int_string_permute_select PREHOOK: type: QUERY -POSTHOOK: query: explain +POSTHOOK: query: explain vectorization detail select insert_num,part,a,b from part_add_int_string_permute_select POSTHOOK: type: QUERY Explain -Plan optimized by CBO. +PLAN VECTORIZATION: + enabled: false + enabledConditionsNotMet: [hive.vectorized.execution.enabled IS false] -Stage-0 - Fetch Operator - limit:-1 - Stage-1 - Map 1 llap - File Output Operator [FS_2] - Select Operator [SEL_1] (rows=2 width=4) - Output:["_col0","_col1","_col2","_col3"] - TableScan [TS_0] (rows=2 width=145) - default@part_add_int_string_permute_select,part_add_int_string_permute_select,Tbl:COMPLETE,Col:PARTIAL,Output:["insert_num","a","b"] +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: part_add_int_string_permute_select + Statistics: Num rows: 2 Data size: 290 Basic stats: COMPLETE Column stats: PARTIAL + Select Operator + expressions: insert_num (type: int), part (type: int), a (type: int), b (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: PARTIAL + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: PARTIAL + 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 + Execution mode: llap + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink PREHOOK: query: select insert_num,part,a,b from part_add_int_string_permute_select PREHOOK: type: QUERY @@ -321,25 +369,49 @@ POSTHOOK: Lineage: part_change_string_group_double PARTITION(part=1).c2 SIMPLE [ POSTHOOK: Lineage: part_change_string_group_double PARTITION(part=1).c3 SIMPLE [(schema_evolution_data)schema_evolution_data.FieldSchema(name:double1, type:double, comment:null), ] POSTHOOK: Lineage: part_change_string_group_double PARTITION(part=1).insert_num SIMPLE [(schema_evolution_data)schema_evolution_data.FieldSchema(name:insert_num, type:int, comment:null), ] insert_num double1 double1 double1 _c4 -PREHOOK: query: explain +PREHOOK: query: explain vectorization detail select insert_num,part,c1,c2,c3,b from part_change_string_group_double PREHOOK: type: QUERY -POSTHOOK: query: explain +POSTHOOK: query: explain vectorization detail select insert_num,part,c1,c2,c3,b from part_change_string_group_double POSTHOOK: type: QUERY Explain -Plan optimized by CBO. +PLAN VECTORIZATION: + enabled: false + enabledConditionsNotMet: [hive.vectorized.execution.enabled IS false] + +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 -Stage-0 - Fetch Operator - limit:-1 - Stage-1 - Map 1 llap - File Output Operator [FS_2] - Select Operator [SEL_1] (rows=5 width=4) - Output:["_col0","_col1","_col2","_col3","_col4","_col5"] - TableScan [TS_0] (rows=5 width=426) - default@part_change_string_group_double,part_change_string_group_double,Tbl:COMPLETE,Col:PARTIAL,Output:["insert_num","c1","c2","c3","b"] +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: part_change_string_group_double + Statistics: Num rows: 5 Data size: 2130 Basic stats: COMPLETE Column stats: PARTIAL + Select Operator + expressions: insert_num (type: int), part (type: int), c1 (type: double), c2 (type: double), c3 (type: double), b (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: PARTIAL + File Output Operator + compressed: false + Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: PARTIAL + 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 + Execution mode: llap + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink PREHOOK: query: select insert_num,part,c1,c2,c3,b from part_change_string_group_double PREHOOK: type: QUERY @@ -421,25 +493,49 @@ POSTHOOK: Lineage: part_change_date_group_string_group_date_timestamp PARTITION( POSTHOOK: Lineage: part_change_date_group_string_group_date_timestamp PARTITION(part=1).c9 EXPRESSION [(values__tmp__table__5)values__tmp__table__5.FieldSchema(name:tmp_values_col10, type:string, comment:), ] POSTHOOK: Lineage: part_change_date_group_string_group_date_timestamp PARTITION(part=1).insert_num EXPRESSION [(values__tmp__table__5)values__tmp__table__5.FieldSchema(name:tmp_values_col1, type:string, comment:), ] _col0 _col1 _col2 _col3 _col4 _col5 _col6 _col7 _col8 _col9 _col10 _col11 -PREHOOK: query: explain +PREHOOK: query: explain vectorization detail select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,b from part_change_date_group_string_group_date_timestamp PREHOOK: type: QUERY -POSTHOOK: query: explain +POSTHOOK: query: explain vectorization detail select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,b from part_change_date_group_string_group_date_timestamp POSTHOOK: type: QUERY Explain -Plan optimized by CBO. +PLAN VECTORIZATION: + enabled: false + enabledConditionsNotMet: [hive.vectorized.execution.enabled IS false] -Stage-0 - Fetch Operator - limit:-1 - Stage-1 - Map 1 llap - File Output Operator [FS_2] - Select Operator [SEL_1] (rows=6 width=4) - Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12"] - TableScan [TS_0] (rows=6 width=586) - default@part_change_date_group_string_group_date_timestamp,part_change_date_group_string_group_date_timestamp,Tbl:COMPLETE,Col:PARTIAL,Output:["insert_num","c1","c2","c3","c4","c5","c6","c7","c8","c9","c10","b"] +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: part_change_date_group_string_group_date_timestamp + Statistics: Num rows: 6 Data size: 3521 Basic stats: COMPLETE Column stats: PARTIAL + Select Operator + expressions: insert_num (type: int), part (type: int), c1 (type: string), c2 (type: char(50)), c3 (type: char(15)), c4 (type: varchar(50)), c5 (type: varchar(15)), c6 (type: string), c7 (type: char(50)), c8 (type: char(15)), c9 (type: varchar(50)), c10 (type: varchar(15)), b (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 + Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL + File Output Operator + compressed: false + Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL + 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 + Execution mode: llap + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink PREHOOK: query: select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,b from part_change_date_group_string_group_date_timestamp PREHOOK: type: QUERY @@ -590,25 +686,49 @@ POSTHOOK: Lineage: part_change_numeric_group_string_group_multi_ints_string_grou POSTHOOK: Lineage: part_change_numeric_group_string_group_multi_ints_string_group PARTITION(part=1).c9 EXPRESSION [(values__tmp__table__6)values__tmp__table__6.FieldSchema(name:tmp_values_col10, type:string, comment:), ] POSTHOOK: Lineage: part_change_numeric_group_string_group_multi_ints_string_group PARTITION(part=1).insert_num EXPRESSION [(values__tmp__table__6)values__tmp__table__6.FieldSchema(name:tmp_values_col1, type:string, comment:), ] _col0 _col1 _col2 _col3 _col4 _col5 _col6 _col7 _col8 _col9 _col10 _col11 _col12 _col13 _col14 _col15 _col16 _col17 _col18 _col19 _col20 _col21 -PREHOOK: query: explain +PREHOOK: query: explain vectorization detail select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,c16,c17,c18,c19,c20,b from part_change_numeric_group_string_group_multi_ints_string_group PREHOOK: type: QUERY -POSTHOOK: query: explain +POSTHOOK: query: explain vectorization detail select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,c16,c17,c18,c19,c20,b from part_change_numeric_group_string_group_multi_ints_string_group POSTHOOK: type: QUERY Explain -Plan optimized by CBO. +PLAN VECTORIZATION: + enabled: false + enabledConditionsNotMet: [hive.vectorized.execution.enabled IS false] + +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 -Stage-0 - Fetch Operator - limit:-1 - Stage-1 - Map 1 llap - File Output Operator [FS_2] - Select Operator [SEL_1] (rows=6 width=4) - Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17","_col18","_col19","_col20","_col21","_col22"] - TableScan [TS_0] (rows=6 width=483) - default@part_change_numeric_group_string_group_multi_ints_string_group,part_change_numeric_group_string_group_multi_ints_string_group,Tbl:COMPLETE,Col:PARTIAL,Output:["insert_num","c1","c2","c3","c4","c5","c6","c7","c8","c9","c10","c11","c12","c13","c14","c15","c16","c17","c18","c19","c20","b"] +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: part_change_numeric_group_string_group_multi_ints_string_group + Statistics: Num rows: 6 Data size: 2903 Basic stats: COMPLETE Column stats: PARTIAL + Select Operator + expressions: insert_num (type: int), part (type: int), c1 (type: string), c2 (type: string), c3 (type: string), c4 (type: string), c5 (type: char(50)), c6 (type: char(50)), c7 (type: char(50)), c8 (type: char(50)), c9 (type: char(5)), c10 (type: char(5)), c11 (type: char(5)), c12 (type: char(5)), c13 (type: varchar(50)), c14 (type: varchar(50)), c15 (type: varchar(50)), c16 (type: varchar(50)), c17 (type: varchar(5)), c18 (type: varchar(5)), c19 (type: varchar(5)), c20 (type: varchar(5)), b (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22 + Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL + File Output Operator + compressed: false + Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL + 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 + Execution mode: llap + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink PREHOOK: query: select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,c16,c17,c18,c19,c20,b from part_change_numeric_group_string_group_multi_ints_string_group PREHOOK: type: QUERY @@ -749,25 +869,49 @@ POSTHOOK: Lineage: part_change_numeric_group_string_group_floating_string_group POSTHOOK: Lineage: part_change_numeric_group_string_group_floating_string_group PARTITION(part=1).c9 EXPRESSION [(values__tmp__table__7)values__tmp__table__7.FieldSchema(name:tmp_values_col10, type:string, comment:), ] POSTHOOK: Lineage: part_change_numeric_group_string_group_floating_string_group PARTITION(part=1).insert_num EXPRESSION [(values__tmp__table__7)values__tmp__table__7.FieldSchema(name:tmp_values_col1, type:string, comment:), ] _col0 _col1 _col2 _col3 _col4 _col5 _col6 _col7 _col8 _col9 _col10 _col11 _col12 _col13 _col14 _col15 _col16 -PREHOOK: query: explain +PREHOOK: query: explain vectorization detail select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,b from part_change_numeric_group_string_group_floating_string_group PREHOOK: type: QUERY -POSTHOOK: query: explain +POSTHOOK: query: explain vectorization detail select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,b from part_change_numeric_group_string_group_floating_string_group POSTHOOK: type: QUERY Explain -Plan optimized by CBO. +PLAN VECTORIZATION: + enabled: false + enabledConditionsNotMet: [hive.vectorized.execution.enabled IS false] + +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: part_change_numeric_group_string_group_floating_string_group + Statistics: Num rows: 6 Data size: 4540 Basic stats: COMPLETE Column stats: PARTIAL + Select Operator + expressions: insert_num (type: int), part (type: int), c1 (type: string), c2 (type: string), c3 (type: string), c4 (type: char(50)), c5 (type: char(50)), c6 (type: char(50)), c7 (type: char(7)), c8 (type: char(7)), c9 (type: char(7)), c10 (type: varchar(50)), c11 (type: varchar(50)), c12 (type: varchar(50)), c13 (type: varchar(7)), c14 (type: varchar(7)), c15 (type: varchar(7)), b (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17 + Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL + File Output Operator + compressed: false + Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL + 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 + Execution mode: llap -Stage-0 - Fetch Operator - limit:-1 - Stage-1 - Map 1 llap - File Output Operator [FS_2] - Select Operator [SEL_1] (rows=6 width=4) - Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17"] - TableScan [TS_0] (rows=6 width=756) - default@part_change_numeric_group_string_group_floating_string_group,part_change_numeric_group_string_group_floating_string_group,Tbl:COMPLETE,Col:PARTIAL,Output:["insert_num","c1","c2","c3","c4","c5","c6","c7","c8","c9","c10","c11","c12","c13","c14","c15","b"] + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink PREHOOK: query: select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,b from part_change_numeric_group_string_group_floating_string_group PREHOOK: type: QUERY @@ -894,25 +1038,49 @@ POSTHOOK: Lineage: part_change_string_group_string_group_string PARTITION(part=1 POSTHOOK: Lineage: part_change_string_group_string_group_string PARTITION(part=1).c9 EXPRESSION [(values__tmp__table__8)values__tmp__table__8.FieldSchema(name:tmp_values_col10, type:string, comment:), ] POSTHOOK: Lineage: part_change_string_group_string_group_string PARTITION(part=1).insert_num EXPRESSION [(values__tmp__table__8)values__tmp__table__8.FieldSchema(name:tmp_values_col1, type:string, comment:), ] _col0 _col1 _col2 _col3 _col4 _col5 _col6 _col7 _col8 _col9 _col10 _col11 -PREHOOK: query: explain +PREHOOK: query: explain vectorization detail select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,b from part_change_string_group_string_group_string PREHOOK: type: QUERY -POSTHOOK: query: explain +POSTHOOK: query: explain vectorization detail select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,b from part_change_string_group_string_group_string POSTHOOK: type: QUERY Explain -Plan optimized by CBO. +PLAN VECTORIZATION: + enabled: false + enabledConditionsNotMet: [hive.vectorized.execution.enabled IS false] + +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: part_change_string_group_string_group_string + Statistics: Num rows: 6 Data size: 6682 Basic stats: COMPLETE Column stats: PARTIAL + Select Operator + expressions: insert_num (type: int), part (type: int), c1 (type: char(50)), c2 (type: char(9)), c3 (type: varchar(50)), c4 (type: char(9)), c5 (type: varchar(50)), c6 (type: varchar(9)), c7 (type: string), c8 (type: char(50)), c9 (type: char(9)), c10 (type: string), b (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 + Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL + File Output Operator + compressed: false + Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL + 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 + Execution mode: llap -Stage-0 - Fetch Operator - limit:-1 - Stage-1 - Map 1 llap - File Output Operator [FS_2] - Select Operator [SEL_1] (rows=6 width=4) - Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12"] - TableScan [TS_0] (rows=6 width=1113) - default@part_change_string_group_string_group_string,part_change_string_group_string_group_string,Tbl:COMPLETE,Col:PARTIAL,Output:["insert_num","c1","c2","c3","c4","c5","c6","c7","c8","c9","c10","b"] + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink PREHOOK: query: select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,b from part_change_string_group_string_group_string PREHOOK: type: QUERY @@ -1067,25 +1235,49 @@ POSTHOOK: Lineage: part_change_lower_to_higher_numeric_group_tinyint_to_bigint P POSTHOOK: Lineage: part_change_lower_to_higher_numeric_group_tinyint_to_bigint PARTITION(part=1).c9 EXPRESSION [(values__tmp__table__9)values__tmp__table__9.FieldSchema(name:tmp_values_col10, type:string, comment:), ] POSTHOOK: Lineage: part_change_lower_to_higher_numeric_group_tinyint_to_bigint PARTITION(part=1).insert_num EXPRESSION [(values__tmp__table__9)values__tmp__table__9.FieldSchema(name:tmp_values_col1, type:string, comment:), ] _col0 _col1 _col2 _col3 _col4 _col5 _col6 _col7 _col8 _col9 _col10 _col11 _col12 _col13 _col14 _col15 _col16 _col17 _col18 _col19 -PREHOOK: query: explain +PREHOOK: query: explain vectorization detail select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,c16,c17,c18,b from part_change_lower_to_higher_numeric_group_tinyint_to_bigint PREHOOK: type: QUERY -POSTHOOK: query: explain +POSTHOOK: query: explain vectorization detail select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,c16,c17,c18,b from part_change_lower_to_higher_numeric_group_tinyint_to_bigint POSTHOOK: type: QUERY Explain -Plan optimized by CBO. +PLAN VECTORIZATION: + enabled: false + enabledConditionsNotMet: [hive.vectorized.execution.enabled IS false] -Stage-0 - Fetch Operator - limit:-1 - Stage-1 - Map 1 llap - File Output Operator [FS_2] - Select Operator [SEL_1] (rows=6 width=4) - Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17","_col18","_col19","_col20"] - TableScan [TS_0] (rows=6 width=236) - default@part_change_lower_to_higher_numeric_group_tinyint_to_bigint,part_change_lower_to_higher_numeric_group_tinyint_to_bigint,Tbl:COMPLETE,Col:PARTIAL,Output:["insert_num","c1","c2","c3","c4","c5","c6","c7","c8","c9","c10","c11","c12","c13","c14","c15","c16","c17","c18","b"] +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: part_change_lower_to_higher_numeric_group_tinyint_to_bigint + Statistics: Num rows: 6 Data size: 1419 Basic stats: COMPLETE Column stats: PARTIAL + Select Operator + expressions: insert_num (type: int), part (type: int), c1 (type: smallint), c2 (type: int), c3 (type: bigint), c4 (type: decimal(38,18)), c5 (type: float), c6 (type: double), c7 (type: int), c8 (type: bigint), c9 (type: decimal(38,18)), c10 (type: float), c11 (type: double), c12 (type: bigint), c13 (type: decimal(38,18)), c14 (type: float), c15 (type: double), c16 (type: decimal(38,18)), c17 (type: float), c18 (type: double), b (type: string) + 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: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL + File Output Operator + compressed: false + Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL + 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 + Execution mode: llap + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink PREHOOK: query: select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,c16,c17,c18,b from part_change_lower_to_higher_numeric_group_tinyint_to_bigint PREHOOK: type: QUERY @@ -1182,25 +1374,49 @@ POSTHOOK: Lineage: part_change_lower_to_higher_numeric_group_decimal_to_float PA POSTHOOK: Lineage: part_change_lower_to_higher_numeric_group_decimal_to_float PARTITION(part=1).c3 EXPRESSION [(values__tmp__table__10)values__tmp__table__10.FieldSchema(name:tmp_values_col4, type:string, comment:), ] POSTHOOK: Lineage: part_change_lower_to_higher_numeric_group_decimal_to_float PARTITION(part=1).insert_num EXPRESSION [(values__tmp__table__10)values__tmp__table__10.FieldSchema(name:tmp_values_col1, type:string, comment:), ] _col0 _col1 _col2 _col3 _col4 -PREHOOK: query: explain +PREHOOK: query: explain vectorization detail select insert_num,part,c1,c2,c3,b from part_change_lower_to_higher_numeric_group_decimal_to_float PREHOOK: type: QUERY -POSTHOOK: query: explain +POSTHOOK: query: explain vectorization detail select insert_num,part,c1,c2,c3,b from part_change_lower_to_higher_numeric_group_decimal_to_float POSTHOOK: type: QUERY Explain -Plan optimized by CBO. +PLAN VECTORIZATION: + enabled: false + enabledConditionsNotMet: [hive.vectorized.execution.enabled IS false] + +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: part_change_lower_to_higher_numeric_group_decimal_to_float + Statistics: Num rows: 6 Data size: 1523 Basic stats: COMPLETE Column stats: PARTIAL + Select Operator + expressions: insert_num (type: int), part (type: int), c1 (type: float), c2 (type: double), c3 (type: double), b (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL + File Output Operator + compressed: false + Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL + 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 + Execution mode: llap -Stage-0 - Fetch Operator - limit:-1 - Stage-1 - Map 1 llap - File Output Operator [FS_2] - Select Operator [SEL_1] (rows=6 width=4) - Output:["_col0","_col1","_col2","_col3","_col4","_col5"] - TableScan [TS_0] (rows=6 width=253) - default@part_change_lower_to_higher_numeric_group_decimal_to_float,part_change_lower_to_higher_numeric_group_decimal_to_float,Tbl:COMPLETE,Col:PARTIAL,Output:["insert_num","c1","c2","c3","b"] + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink PREHOOK: query: select insert_num,part,c1,c2,c3,b from part_change_lower_to_higher_numeric_group_decimal_to_float PREHOOK: type: QUERY diff --git ql/src/test/results/clientpositive/llap/schema_evol_orc_nonvec_part_all_complex.q.out ql/src/test/results/clientpositive/llap/schema_evol_orc_nonvec_part_all_complex.q.out index 3da9284..22c7745 100644 --- ql/src/test/results/clientpositive/llap/schema_evol_orc_nonvec_part_all_complex.q.out +++ ql/src/test/results/clientpositive/llap/schema_evol_orc_nonvec_part_all_complex.q.out @@ -131,25 +131,49 @@ POSTHOOK: Lineage: part_change_various_various_struct1 PARTITION(part=1).b SIMPL POSTHOOK: Lineage: part_change_various_various_struct1 PARTITION(part=1).insert_num SIMPLE [(complex_struct1_c_txt)complex_struct1_c_txt.FieldSchema(name:insert_num, type:int, comment:null), ] POSTHOOK: Lineage: part_change_various_various_struct1 PARTITION(part=1).s1 SIMPLE [(complex_struct1_c_txt)complex_struct1_c_txt.FieldSchema(name:s1, type:struct, comment:null), ] complex_struct1_c_txt.insert_num complex_struct1_c_txt.s1 complex_struct1_c_txt.b -PREHOOK: query: explain +PREHOOK: query: explain vectorization detail select insert_num,part,s1,b from part_change_various_various_struct1 PREHOOK: type: QUERY -POSTHOOK: query: explain +POSTHOOK: query: explain vectorization detail select insert_num,part,s1,b from part_change_various_various_struct1 POSTHOOK: type: QUERY Explain -Plan optimized by CBO. +PLAN VECTORIZATION: + enabled: false + enabledConditionsNotMet: [hive.vectorized.execution.enabled IS false] -Stage-0 - Fetch Operator - limit:-1 - Stage-1 - Map 1 llap - File Output Operator [FS_2] - Select Operator [SEL_1] (rows=6 width=4) - Output:["_col0","_col1","_col2","_col3"] - TableScan [TS_0] (rows=6 width=789) - default@part_change_various_various_struct1,part_change_various_various_struct1,Tbl:COMPLETE,Col:PARTIAL,Output:["insert_num","s1","b"] +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: part_change_various_various_struct1 + Statistics: Num rows: 6 Data size: 4734 Basic stats: COMPLETE Column stats: PARTIAL + Select Operator + expressions: insert_num (type: int), part (type: int), s1 (type: struct), b (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL + File Output Operator + compressed: false + Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL + 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 + Execution mode: llap + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink PREHOOK: query: select insert_num,part,s1,b from part_change_various_various_struct1 PREHOOK: type: QUERY @@ -383,25 +407,49 @@ POSTHOOK: Lineage: part_add_various_various_struct2 PARTITION(part=1).b SIMPLE [ POSTHOOK: Lineage: part_add_various_various_struct2 PARTITION(part=1).insert_num SIMPLE [(complex_struct2_d_txt)complex_struct2_d_txt.FieldSchema(name:insert_num, type:int, comment:null), ] POSTHOOK: Lineage: part_add_various_various_struct2 PARTITION(part=1).s2 SIMPLE [(complex_struct2_d_txt)complex_struct2_d_txt.FieldSchema(name:s2, type:struct, comment:null), ] complex_struct2_d_txt.insert_num complex_struct2_d_txt.b complex_struct2_d_txt.s2 -PREHOOK: query: explain +PREHOOK: query: explain vectorization detail select insert_num,part,b,s2 from part_add_various_various_struct2 PREHOOK: type: QUERY -POSTHOOK: query: explain +POSTHOOK: query: explain vectorization detail select insert_num,part,b,s2 from part_add_various_various_struct2 POSTHOOK: type: QUERY Explain -Plan optimized by CBO. +PLAN VECTORIZATION: + enabled: false + enabledConditionsNotMet: [hive.vectorized.execution.enabled IS false] + +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 -Stage-0 - Fetch Operator - limit:-1 - Stage-1 - Map 1 llap - File Output Operator [FS_2] - Select Operator [SEL_1] (rows=8 width=4) - Output:["_col0","_col1","_col2","_col3"] - TableScan [TS_0] (rows=8 width=614) - default@part_add_various_various_struct2,part_add_various_various_struct2,Tbl:COMPLETE,Col:PARTIAL,Output:["insert_num","b","s2"] +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: part_add_various_various_struct2 + Statistics: Num rows: 8 Data size: 4912 Basic stats: COMPLETE Column stats: PARTIAL + Select Operator + expressions: insert_num (type: int), part (type: int), b (type: string), s2 (type: struct) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 8 Data size: 32 Basic stats: COMPLETE Column stats: PARTIAL + File Output Operator + compressed: false + Statistics: Num rows: 8 Data size: 32 Basic stats: COMPLETE Column stats: PARTIAL + 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 + Execution mode: llap + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink PREHOOK: query: select insert_num,part,b,s2 from part_add_various_various_struct2 PREHOOK: type: QUERY @@ -563,25 +611,49 @@ POSTHOOK: Lineage: part_add_to_various_various_struct4 PARTITION(part=1).b SIMPL POSTHOOK: Lineage: part_add_to_various_various_struct4 PARTITION(part=1).insert_num SIMPLE [(complex_struct4_c_txt)complex_struct4_c_txt.FieldSchema(name:insert_num, type:int, comment:null), ] POSTHOOK: Lineage: part_add_to_various_various_struct4 PARTITION(part=1).s3 SIMPLE [(complex_struct4_c_txt)complex_struct4_c_txt.FieldSchema(name:s3, type:struct, comment:null), ] complex_struct4_c_txt.insert_num complex_struct4_c_txt.b complex_struct4_c_txt.s3 -PREHOOK: query: explain +PREHOOK: query: explain vectorization detail select insert_num,part,b,s3 from part_add_to_various_various_struct4 PREHOOK: type: QUERY -POSTHOOK: query: explain +POSTHOOK: query: explain vectorization detail select insert_num,part,b,s3 from part_add_to_various_various_struct4 POSTHOOK: type: QUERY Explain -Plan optimized by CBO. +PLAN VECTORIZATION: + enabled: false + enabledConditionsNotMet: [hive.vectorized.execution.enabled IS false] + +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: part_add_to_various_various_struct4 + Statistics: Num rows: 4 Data size: 1172 Basic stats: COMPLETE Column stats: PARTIAL + Select Operator + expressions: insert_num (type: int), part (type: int), b (type: string), s3 (type: struct) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: PARTIAL + File Output Operator + compressed: false + Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: PARTIAL + 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 + Execution mode: llap -Stage-0 - Fetch Operator - limit:-1 - Stage-1 - Map 1 llap - File Output Operator [FS_2] - Select Operator [SEL_1] (rows=4 width=4) - Output:["_col0","_col1","_col2","_col3"] - TableScan [TS_0] (rows=4 width=293) - default@part_add_to_various_various_struct4,part_add_to_various_various_struct4,Tbl:COMPLETE,Col:PARTIAL,Output:["insert_num","b","s3"] + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink PREHOOK: query: select insert_num,part,b,s3 from part_add_to_various_various_struct4 PREHOOK: type: QUERY diff --git ql/src/test/results/clientpositive/llap/schema_evol_orc_nonvec_part_all_primitive.q.out ql/src/test/results/clientpositive/llap/schema_evol_orc_nonvec_part_all_primitive.q.out index 526cd21..4e94322 100644 --- ql/src/test/results/clientpositive/llap/schema_evol_orc_nonvec_part_all_primitive.q.out +++ ql/src/test/results/clientpositive/llap/schema_evol_orc_nonvec_part_all_primitive.q.out @@ -242,25 +242,49 @@ POSTHOOK: Lineage: part_change_various_various_boolean_to_bigint PARTITION(part= POSTHOOK: Lineage: part_change_various_various_boolean_to_bigint PARTITION(part=1).c9 SIMPLE [(schema_evolution_data)schema_evolution_data.FieldSchema(name:boolean1, type:boolean, comment:null), ] POSTHOOK: Lineage: part_change_various_various_boolean_to_bigint PARTITION(part=1).insert_num SIMPLE [(schema_evolution_data)schema_evolution_data.FieldSchema(name:insert_num, type:int, comment:null), ] insert_num boolean1 boolean1 boolean1 boolean1 boolean1 boolean1 boolean1 boolean1 boolean1 tinyint1 tinyint1 tinyint1 tinyint1 tinyint1 tinyint1 tinyint1 tinyint1 tinyint1 tinyint1 tinyint1 smallint1 smallint1 smallint1 smallint1 smallint1 smallint1 smallint1 smallint1 smallint1 smallint1 smallint1 int1 int1 int1 int1 int1 int1 int1 int1 int1 int1 int1 bigint1 bigint1 bigint1 bigint1 bigint1 bigint1 bigint1 bigint1 bigint1 bigint1 bigint1 _c54 -PREHOOK: query: explain +PREHOOK: query: explain vectorization detail select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,c16,c17,c18,c19,c20,c21,c22,c23,c24,c25,c26,c27,c28,c29,c30,c31,c32,c33,c34,c35,c36,c37,c38,c39,c40,c41,c42,c43,c44,c45,c46,c47,c48,c49,c50,c51,c52,c53,b from part_change_various_various_boolean_to_bigint PREHOOK: type: QUERY -POSTHOOK: query: explain +POSTHOOK: query: explain vectorization detail select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,c16,c17,c18,c19,c20,c21,c22,c23,c24,c25,c26,c27,c28,c29,c30,c31,c32,c33,c34,c35,c36,c37,c38,c39,c40,c41,c42,c43,c44,c45,c46,c47,c48,c49,c50,c51,c52,c53,b from part_change_various_various_boolean_to_bigint POSTHOOK: type: QUERY Explain -Plan optimized by CBO. +PLAN VECTORIZATION: + enabled: false + enabledConditionsNotMet: [hive.vectorized.execution.enabled IS false] -Stage-0 - Fetch Operator - limit:-1 - Stage-1 - Map 1 llap - File Output Operator [FS_2] - Select Operator [SEL_1] (rows=10 width=4) - Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17","_col18","_col19","_col20","_col21","_col22","_col23","_col24","_col25","_col26","_col27","_col28","_col29","_col30","_col31","_col32","_col33","_col34","_col35","_col36","_col37","_col38","_col39","_col40","_col41","_col42","_col43","_col44","_col45","_col46","_col47","_col48","_col49","_col50","_col51","_col52","_col53","_col54","_col55"] - TableScan [TS_0] (rows=10 width=1168) - default@part_change_various_various_boolean_to_bigint,part_change_various_various_boolean_to_bigint,Tbl:COMPLETE,Col:PARTIAL,Output:["insert_num","c1","c2","c3","c4","c5","c6","c7","c8","c9","c10","c11","c12","c13","c14","c15","c16","c17","c18","c19","c20","c21","c22","c23","c24","c25","c26","c27","c28","c29","c30","c31","c32","c33","c34","c35","c36","c37","c38","c39","c40","c41","c42","c43","c44","c45","c46","c47","c48","c49","c50","c51","c52","c53","b"] +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: part_change_various_various_boolean_to_bigint + Statistics: Num rows: 10 Data size: 11688 Basic stats: COMPLETE Column stats: PARTIAL + Select Operator + expressions: insert_num (type: int), part (type: int), c1 (type: boolean), c2 (type: boolean), c3 (type: boolean), c4 (type: boolean), c5 (type: boolean), c6 (type: boolean), c7 (type: boolean), c8 (type: boolean), c9 (type: boolean), c10 (type: tinyint), c11 (type: tinyint), c12 (type: tinyint), c13 (type: tinyint), c14 (type: tinyint), c15 (type: tinyint), c16 (type: tinyint), c17 (type: tinyint), c18 (type: tinyint), c19 (type: tinyint), c20 (type: tinyint), c21 (type: smallint), c22 (type: smallint), c23 (type: smallint), c24 (type: smallint), c25 (type: smallint), c26 (type: smallint), c27 (type: smallint), c28 (type: smallint), c29 (type: smallint), c30 (type: smallint), c31 (type: smallint), c32 (type: int), c33 (type: int), c34 (type: int), c35 (type: int), c36 (type: int), c37 (type: int), c38 (type: int), c39 (type: int), c40 (type: int), c41 (type: int), c42 (type: int), c43 (type: bigint), c44 (type: bigint), c45 (type: bigint), c46 (type: bigint), c47 (type: bigint), c48 (type: bigint), c49 (type: bigint), c50 (type: bigint), c51 (type: bigint), c52 (type: bigint), c53 (type: bigint), b (type: string) + 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, _col24, _col25, _col26, _col27, _col28, _col29, _col30, _col31, _col32, _col33, _col34, _col35, _col36, _col37, _col38, _col39, _col40, _col41, _col42, _col43, _col44, _col45, _col46, _col47, _col48, _col49, _col50, _col51, _col52, _col53, _col54, _col55 + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: PARTIAL + File Output Operator + compressed: false + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: PARTIAL + 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 + Execution mode: llap + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink PREHOOK: query: select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,c16,c17,c18,c19,c20,c21,c22,c23,c24,c25,c26,c27,c28,c29,c30,c31,c32,c33,c34,c35,c36,c37,c38,c39,c40,c41,c42,c43,c44,c45,c46,c47,c48,c49,c50,c51,c52,c53,b from part_change_various_various_boolean_to_bigint PREHOOK: type: QUERY @@ -443,25 +467,49 @@ POSTHOOK: Lineage: part_change_various_various_decimal_to_double PARTITION(part= POSTHOOK: Lineage: part_change_various_various_decimal_to_double PARTITION(part=1).c9 SIMPLE [(schema_evolution_data_2)schema_evolution_data_2.FieldSchema(name:decimal1, type:decimal(38,18), comment:null), ] POSTHOOK: Lineage: part_change_various_various_decimal_to_double PARTITION(part=1).insert_num SIMPLE [(schema_evolution_data_2)schema_evolution_data_2.FieldSchema(name:insert_num, type:int, comment:null), ] insert_num decimal1 decimal1 decimal1 decimal1 decimal1 decimal1 decimal1 decimal1 decimal1 decimal1 decimal1 float1 float1 float1 float1 float1 float1 float1 float1 float1 float1 float1 double1 double1 double1 double1 double1 double1 double1 double1 double1 double1 double1 _c34 -PREHOOK: query: explain +PREHOOK: query: explain vectorization detail select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,c16,c17,c18,c19,c20,c21,c22,c23,c24,c25,c26,c27,c28,c29,c30,c31,c32,c33,b from part_change_various_various_decimal_to_double PREHOOK: type: QUERY -POSTHOOK: query: explain +POSTHOOK: query: explain vectorization detail select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,c16,c17,c18,c19,c20,c21,c22,c23,c24,c25,c26,c27,c28,c29,c30,c31,c32,c33,b from part_change_various_various_decimal_to_double POSTHOOK: type: QUERY Explain -Plan optimized by CBO. +PLAN VECTORIZATION: + enabled: false + enabledConditionsNotMet: [hive.vectorized.execution.enabled IS false] + +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 -Stage-0 - Fetch Operator - limit:-1 - Stage-1 - Map 1 llap - File Output Operator [FS_2] - Select Operator [SEL_1] (rows=6 width=4) - Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17","_col18","_col19","_col20","_col21","_col22","_col23","_col24","_col25","_col26","_col27","_col28","_col29","_col30","_col31","_col32","_col33","_col34","_col35"] - TableScan [TS_0] (rows=6 width=1382) - default@part_change_various_various_decimal_to_double,part_change_various_various_decimal_to_double,Tbl:COMPLETE,Col:PARTIAL,Output:["insert_num","c1","c2","c3","c4","c5","c6","c7","c8","c9","c10","c11","c12","c13","c14","c15","c16","c17","c18","c19","c20","c21","c22","c23","c24","c25","c26","c27","c28","c29","c30","c31","c32","c33","b"] +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: part_change_various_various_decimal_to_double + Statistics: Num rows: 6 Data size: 8295 Basic stats: COMPLETE Column stats: PARTIAL + Select Operator + expressions: insert_num (type: int), part (type: int), c1 (type: decimal(38,18)), c2 (type: decimal(38,18)), c3 (type: decimal(38,18)), c4 (type: decimal(38,18)), c5 (type: decimal(38,18)), c6 (type: decimal(38,18)), c7 (type: decimal(38,18)), c8 (type: decimal(38,18)), c9 (type: decimal(38,18)), c10 (type: decimal(38,18)), c11 (type: decimal(38,18)), c12 (type: float), c13 (type: float), c14 (type: float), c15 (type: float), c16 (type: float), c17 (type: float), c18 (type: float), c19 (type: float), c20 (type: float), c21 (type: float), c22 (type: float), c23 (type: double), c24 (type: double), c25 (type: double), c26 (type: double), c27 (type: double), c28 (type: double), c29 (type: double), c30 (type: double), c31 (type: double), c32 (type: double), c33 (type: double), b (type: string) + 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, _col24, _col25, _col26, _col27, _col28, _col29, _col30, _col31, _col32, _col33, _col34, _col35 + Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL + File Output Operator + compressed: false + Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL + 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 + Execution mode: llap + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink PREHOOK: query: select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,c16,c17,c18,c19,c20,c21,c22,c23,c24,c25,c26,c27,c28,c29,c30,c31,c32,c33,b from part_change_various_various_decimal_to_double PREHOOK: type: QUERY @@ -566,25 +614,49 @@ POSTHOOK: Lineage: part_change_various_various_timestamp PARTITION(part=1).c8 SI POSTHOOK: Lineage: part_change_various_various_timestamp PARTITION(part=1).c9 SIMPLE [(schema_evolution_data_2)schema_evolution_data_2.FieldSchema(name:timestamp1, type:timestamp, comment:null), ] POSTHOOK: Lineage: part_change_various_various_timestamp PARTITION(part=1).insert_num SIMPLE [(schema_evolution_data_2)schema_evolution_data_2.FieldSchema(name:insert_num, type:int, comment:null), ] insert_num timestamp1 timestamp1 timestamp1 timestamp1 timestamp1 timestamp1 timestamp1 timestamp1 timestamp1 timestamp1 timestamp1 timestamp1 _c13 -PREHOOK: query: explain +PREHOOK: query: explain vectorization detail select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,b from part_change_various_various_timestamp PREHOOK: type: QUERY -POSTHOOK: query: explain +POSTHOOK: query: explain vectorization detail select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,b from part_change_various_various_timestamp POSTHOOK: type: QUERY Explain -Plan optimized by CBO. +PLAN VECTORIZATION: + enabled: false + enabledConditionsNotMet: [hive.vectorized.execution.enabled IS false] -Stage-0 - Fetch Operator - limit:-1 - Stage-1 - Map 1 llap - File Output Operator [FS_2] - Select Operator [SEL_1] (rows=6 width=4) - Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14"] - TableScan [TS_0] (rows=6 width=494) - default@part_change_various_various_timestamp,part_change_various_various_timestamp,Tbl:COMPLETE,Col:PARTIAL,Output:["insert_num","c1","c2","c3","c4","c5","c6","c7","c8","c9","c10","c11","c12","b"] +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: part_change_various_various_timestamp + Statistics: Num rows: 6 Data size: 2965 Basic stats: COMPLETE Column stats: PARTIAL + Select Operator + expressions: insert_num (type: int), part (type: int), c1 (type: timestamp), c2 (type: timestamp), c3 (type: timestamp), c4 (type: timestamp), c5 (type: timestamp), c6 (type: timestamp), c7 (type: timestamp), c8 (type: timestamp), c9 (type: timestamp), c10 (type: timestamp), c11 (type: timestamp), c12 (type: timestamp), b (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14 + Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL + File Output Operator + compressed: false + Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL + 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 + Execution mode: llap + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink PREHOOK: query: select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,b from part_change_various_various_timestamp PREHOOK: type: QUERY @@ -673,25 +745,49 @@ POSTHOOK: Lineage: part_change_various_various_date PARTITION(part=1).c3 SIMPLE POSTHOOK: Lineage: part_change_various_various_date PARTITION(part=1).c4 SIMPLE [(schema_evolution_data_2)schema_evolution_data_2.FieldSchema(name:date1, type:date, comment:null), ] POSTHOOK: Lineage: part_change_various_various_date PARTITION(part=1).insert_num SIMPLE [(schema_evolution_data_2)schema_evolution_data_2.FieldSchema(name:insert_num, type:int, comment:null), ] insert_num date1 date1 date1 date1 _c5 -PREHOOK: query: explain +PREHOOK: query: explain vectorization detail select insert_num,part,c1,c2,c3,c4,b from part_change_various_various_date PREHOOK: type: QUERY -POSTHOOK: query: explain +POSTHOOK: query: explain vectorization detail select insert_num,part,c1,c2,c3,c4,b from part_change_various_various_date POSTHOOK: type: QUERY Explain -Plan optimized by CBO. +PLAN VECTORIZATION: + enabled: false + enabledConditionsNotMet: [hive.vectorized.execution.enabled IS false] + +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: part_change_various_various_date + Statistics: Num rows: 6 Data size: 2444 Basic stats: COMPLETE Column stats: PARTIAL + Select Operator + expressions: insert_num (type: int), part (type: int), c1 (type: date), c2 (type: date), c3 (type: date), c4 (type: date), b (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 + Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL + File Output Operator + compressed: false + Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL + 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 + Execution mode: llap -Stage-0 - Fetch Operator - limit:-1 - Stage-1 - Map 1 llap - File Output Operator [FS_2] - Select Operator [SEL_1] (rows=6 width=4) - Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"] - TableScan [TS_0] (rows=6 width=407) - default@part_change_various_various_date,part_change_various_various_date,Tbl:COMPLETE,Col:PARTIAL,Output:["insert_num","c1","c2","c3","c4","b"] + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink PREHOOK: query: select insert_num,part,c1,c2,c3,c4,b from part_change_various_various_date PREHOOK: type: QUERY @@ -861,25 +957,49 @@ POSTHOOK: Lineage: part_change_same_type_different_params PARTITION(part=2).c5 S POSTHOOK: Lineage: part_change_same_type_different_params PARTITION(part=2).c6 SIMPLE [(same_type1_c_txt)same_type1_c_txt.FieldSchema(name:c6, type:decimal(25,15), comment:null), ] POSTHOOK: Lineage: part_change_same_type_different_params PARTITION(part=2).insert_num SIMPLE [(same_type1_c_txt)same_type1_c_txt.FieldSchema(name:insert_num, type:int, comment:null), ] same_type1_c_txt.insert_num same_type1_c_txt.c1 same_type1_c_txt.c2 same_type1_c_txt.c3 same_type1_c_txt.c4 same_type1_c_txt.c5 same_type1_c_txt.c6 same_type1_c_txt.b -PREHOOK: query: explain +PREHOOK: query: explain vectorization detail select insert_num,part,c1,c2,c3,c4,c5,c6,b from part_change_same_type_different_params PREHOOK: type: QUERY -POSTHOOK: query: explain +POSTHOOK: query: explain vectorization detail select insert_num,part,c1,c2,c3,c4,c5,c6,b from part_change_same_type_different_params POSTHOOK: type: QUERY Explain -Plan optimized by CBO. +PLAN VECTORIZATION: + enabled: false + enabledConditionsNotMet: [hive.vectorized.execution.enabled IS false] + +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: part_change_same_type_different_params + Statistics: Num rows: 13 Data size: 8736 Basic stats: COMPLETE Column stats: PARTIAL + Select Operator + expressions: insert_num (type: int), part (type: int), c1 (type: char(8)), c2 (type: char(32)), c3 (type: varchar(15)), c4 (type: varchar(18)), c5 (type: decimal(10,2)), c6 (type: decimal(25,15)), b (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 + Statistics: Num rows: 13 Data size: 52 Basic stats: COMPLETE Column stats: PARTIAL + File Output Operator + compressed: false + Statistics: Num rows: 13 Data size: 52 Basic stats: COMPLETE Column stats: PARTIAL + 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 + Execution mode: llap -Stage-0 - Fetch Operator - limit:-1 - Stage-1 - Map 1 llap - File Output Operator [FS_2] - Select Operator [SEL_1] (rows=13 width=4) - Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"] - TableScan [TS_0] (rows=13 width=672) - default@part_change_same_type_different_params,part_change_same_type_different_params,Tbl:COMPLETE,Col:PARTIAL,Output:["insert_num","c1","c2","c3","c4","c5","c6","b"] + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink PREHOOK: query: select insert_num,part,c1,c2,c3,c4,c5,c6,b from part_change_same_type_different_params PREHOOK: type: QUERY diff --git ql/src/test/results/clientpositive/llap/schema_evol_orc_nonvec_table.q.out ql/src/test/results/clientpositive/llap/schema_evol_orc_nonvec_table.q.out index 7b420e2..103284e 100644 --- ql/src/test/results/clientpositive/llap/schema_evol_orc_nonvec_table.q.out +++ ql/src/test/results/clientpositive/llap/schema_evol_orc_nonvec_table.q.out @@ -55,25 +55,49 @@ POSTHOOK: Lineage: table_add_int_permute_select.b SIMPLE [(values__tmp__table__1 POSTHOOK: Lineage: table_add_int_permute_select.c EXPRESSION [(values__tmp__table__1)values__tmp__table__1.FieldSchema(name:tmp_values_col4, type:string, comment:), ] POSTHOOK: Lineage: table_add_int_permute_select.insert_num EXPRESSION [(values__tmp__table__1)values__tmp__table__1.FieldSchema(name:tmp_values_col1, type:string, comment:), ] _col0 _col1 _col2 _col3 -PREHOOK: query: explain +PREHOOK: query: explain vectorization detail select insert_num,a,b from table_add_int_permute_select PREHOOK: type: QUERY -POSTHOOK: query: explain +POSTHOOK: query: explain vectorization detail select insert_num,a,b from table_add_int_permute_select POSTHOOK: type: QUERY Explain -Plan optimized by CBO. +PLAN VECTORIZATION: + enabled: false + enabledConditionsNotMet: [hive.vectorized.execution.enabled IS false] -Stage-0 - Fetch Operator - limit:-1 - Stage-1 - Map 1 llap - File Output Operator [FS_2] - Select Operator [SEL_1] (rows=6 width=99) - Output:["_col0","_col1","_col2"] - TableScan [TS_0] (rows=6 width=99) - default@table_add_int_permute_select,table_add_int_permute_select,Tbl:COMPLETE,Col:NONE,Output:["insert_num","a","b"] +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: table_add_int_permute_select + Statistics: Num rows: 6 Data size: 595 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: insert_num (type: int), a (type: int), b (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 6 Data size: 595 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 6 Data size: 595 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 + Execution mode: llap + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink PREHOOK: query: select insert_num,a,b from table_add_int_permute_select PREHOOK: type: QUERY @@ -168,25 +192,49 @@ POSTHOOK: Lineage: table_add_int_string_permute_select.c EXPRESSION [(values__tm POSTHOOK: Lineage: table_add_int_string_permute_select.d SIMPLE [(values__tmp__table__2)values__tmp__table__2.FieldSchema(name:tmp_values_col5, type:string, comment:), ] POSTHOOK: Lineage: table_add_int_string_permute_select.insert_num EXPRESSION [(values__tmp__table__2)values__tmp__table__2.FieldSchema(name:tmp_values_col1, type:string, comment:), ] _col0 _col1 _col2 _col3 _col4 -PREHOOK: query: explain +PREHOOK: query: explain vectorization detail select insert_num,a,b from table_add_int_string_permute_select PREHOOK: type: QUERY -POSTHOOK: query: explain +POSTHOOK: query: explain vectorization detail select insert_num,a,b from table_add_int_string_permute_select POSTHOOK: type: QUERY Explain -Plan optimized by CBO. +PLAN VECTORIZATION: + enabled: false + enabledConditionsNotMet: [hive.vectorized.execution.enabled IS false] + +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 -Stage-0 - Fetch Operator - limit:-1 - Stage-1 - Map 1 llap - File Output Operator [FS_2] - Select Operator [SEL_1] (rows=6 width=114) - Output:["_col0","_col1","_col2"] - TableScan [TS_0] (rows=6 width=114) - default@table_add_int_string_permute_select,table_add_int_string_permute_select,Tbl:COMPLETE,Col:NONE,Output:["insert_num","a","b"] +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: table_add_int_string_permute_select + Statistics: Num rows: 6 Data size: 685 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: insert_num (type: int), a (type: int), b (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 6 Data size: 685 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 6 Data size: 685 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 + Execution mode: llap + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink PREHOOK: query: select insert_num,a,b from table_add_int_string_permute_select PREHOOK: type: QUERY @@ -343,25 +391,49 @@ POSTHOOK: Lineage: table_change_string_group_double.c2 EXPRESSION [(values__tmp_ POSTHOOK: Lineage: table_change_string_group_double.c3 EXPRESSION [(values__tmp__table__3)values__tmp__table__3.FieldSchema(name:tmp_values_col4, type:string, comment:), ] POSTHOOK: Lineage: table_change_string_group_double.insert_num EXPRESSION [(values__tmp__table__3)values__tmp__table__3.FieldSchema(name:tmp_values_col1, type:string, comment:), ] _col0 _col1 _col2 _col3 _col4 -PREHOOK: query: explain +PREHOOK: query: explain vectorization detail select insert_num,c1,c2,c3,b from table_change_string_group_double PREHOOK: type: QUERY -POSTHOOK: query: explain +POSTHOOK: query: explain vectorization detail select insert_num,c1,c2,c3,b from table_change_string_group_double POSTHOOK: type: QUERY Explain -Plan optimized by CBO. +PLAN VECTORIZATION: + enabled: false + enabledConditionsNotMet: [hive.vectorized.execution.enabled IS false] -Stage-0 - Fetch Operator - limit:-1 - Stage-1 - Map 1 llap - File Output Operator [FS_2] - Select Operator [SEL_1] (rows=6 width=370) - Output:["_col0","_col1","_col2","_col3","_col4"] - TableScan [TS_0] (rows=6 width=370) - default@table_change_string_group_double,table_change_string_group_double,Tbl:COMPLETE,Col:NONE,Output:["insert_num","c1","c2","c3","b"] +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: table_change_string_group_double + Statistics: Num rows: 6 Data size: 2225 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: insert_num (type: int), c1 (type: double), c2 (type: double), c3 (type: double), b (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4 + Statistics: Num rows: 6 Data size: 2225 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 6 Data size: 2225 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 + Execution mode: llap + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink PREHOOK: query: select insert_num,c1,c2,c3,b from table_change_string_group_double PREHOOK: type: QUERY @@ -587,25 +659,49 @@ POSTHOOK: Lineage: table_change_numeric_group_string_group_multi_ints_string_gro POSTHOOK: Lineage: table_change_numeric_group_string_group_multi_ints_string_group.c9 EXPRESSION [(values__tmp__table__5)values__tmp__table__5.FieldSchema(name:tmp_values_col10, type:string, comment:), ] POSTHOOK: Lineage: table_change_numeric_group_string_group_multi_ints_string_group.insert_num EXPRESSION [(values__tmp__table__5)values__tmp__table__5.FieldSchema(name:tmp_values_col1, type:string, comment:), ] _col0 _col1 _col2 _col3 _col4 _col5 _col6 _col7 _col8 _col9 _col10 _col11 _col12 _col13 _col14 _col15 _col16 _col17 _col18 _col19 _col20 _col21 -PREHOOK: query: explain +PREHOOK: query: explain vectorization detail select insert_num,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,c16,c17,c18,c19,c20,b from table_change_numeric_group_string_group_multi_ints_string_group PREHOOK: type: QUERY -POSTHOOK: query: explain +POSTHOOK: query: explain vectorization detail select insert_num,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,c16,c17,c18,c19,c20,b from table_change_numeric_group_string_group_multi_ints_string_group POSTHOOK: type: QUERY Explain -Plan optimized by CBO. +PLAN VECTORIZATION: + enabled: false + enabledConditionsNotMet: [hive.vectorized.execution.enabled IS false] + +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: table_change_numeric_group_string_group_multi_ints_string_group + Statistics: Num rows: 6 Data size: 2879 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: insert_num (type: int), c1 (type: string), c2 (type: string), c3 (type: string), c4 (type: string), c5 (type: char(50)), c6 (type: char(50)), c7 (type: char(50)), c8 (type: char(50)), c9 (type: char(5)), c10 (type: char(5)), c11 (type: char(5)), c12 (type: char(5)), c13 (type: varchar(50)), c14 (type: varchar(50)), c15 (type: varchar(50)), c16 (type: varchar(50)), c17 (type: varchar(5)), c18 (type: varchar(5)), c19 (type: varchar(5)), c20 (type: varchar(5)), b (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21 + Statistics: Num rows: 6 Data size: 2879 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 6 Data size: 2879 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 + Execution mode: llap -Stage-0 - Fetch Operator - limit:-1 - Stage-1 - Map 1 llap - File Output Operator [FS_2] - Select Operator [SEL_1] (rows=6 width=479) - Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17","_col18","_col19","_col20","_col21"] - TableScan [TS_0] (rows=6 width=479) - default@table_change_numeric_group_string_group_multi_ints_string_group,table_change_numeric_group_string_group_multi_ints_string_group,Tbl:COMPLETE,Col:NONE,Output:["insert_num","c1","c2","c3","c4","c5","c6","c7","c8","c9","c10","c11","c12","c13","c14","c15","c16","c17","c18","c19","c20","b"] + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink PREHOOK: query: select insert_num,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,c16,c17,c18,c19,c20,b from table_change_numeric_group_string_group_multi_ints_string_group PREHOOK: type: QUERY @@ -742,25 +838,49 @@ POSTHOOK: Lineage: table_change_numeric_group_string_group_floating_string_group POSTHOOK: Lineage: table_change_numeric_group_string_group_floating_string_group.c9 EXPRESSION [(values__tmp__table__6)values__tmp__table__6.FieldSchema(name:tmp_values_col10, type:string, comment:), ] POSTHOOK: Lineage: table_change_numeric_group_string_group_floating_string_group.insert_num EXPRESSION [(values__tmp__table__6)values__tmp__table__6.FieldSchema(name:tmp_values_col1, type:string, comment:), ] _col0 _col1 _col2 _col3 _col4 _col5 _col6 _col7 _col8 _col9 _col10 _col11 _col12 _col13 _col14 _col15 _col16 -PREHOOK: query: explain +PREHOOK: query: explain vectorization detail select insert_num,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,b from table_change_numeric_group_string_group_floating_string_group PREHOOK: type: QUERY -POSTHOOK: query: explain +POSTHOOK: query: explain vectorization detail select insert_num,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,b from table_change_numeric_group_string_group_floating_string_group POSTHOOK: type: QUERY Explain -Plan optimized by CBO. +PLAN VECTORIZATION: + enabled: false + enabledConditionsNotMet: [hive.vectorized.execution.enabled IS false] + +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: table_change_numeric_group_string_group_floating_string_group + Statistics: Num rows: 6 Data size: 4516 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: insert_num (type: int), c1 (type: string), c2 (type: string), c3 (type: string), c4 (type: char(50)), c5 (type: char(50)), c6 (type: char(50)), c7 (type: char(7)), c8 (type: char(7)), c9 (type: char(7)), c10 (type: varchar(50)), c11 (type: varchar(50)), c12 (type: varchar(50)), c13 (type: varchar(7)), c14 (type: varchar(7)), c15 (type: varchar(7)), b (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16 + Statistics: Num rows: 6 Data size: 4516 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 6 Data size: 4516 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 + Execution mode: llap -Stage-0 - Fetch Operator - limit:-1 - Stage-1 - Map 1 llap - File Output Operator [FS_2] - Select Operator [SEL_1] (rows=6 width=752) - Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16"] - TableScan [TS_0] (rows=6 width=752) - default@table_change_numeric_group_string_group_floating_string_group,table_change_numeric_group_string_group_floating_string_group,Tbl:COMPLETE,Col:NONE,Output:["insert_num","c1","c2","c3","c4","c5","c6","c7","c8","c9","c10","c11","c12","c13","c14","c15","b"] + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink PREHOOK: query: select insert_num,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,b from table_change_numeric_group_string_group_floating_string_group PREHOOK: type: QUERY diff --git ql/src/test/results/clientpositive/llap/schema_evol_text_nonvec_part.q.out ql/src/test/results/clientpositive/llap/schema_evol_text_nonvec_part.q.out index 89a66ba..8daee28 100644 --- ql/src/test/results/clientpositive/llap/schema_evol_text_nonvec_part.q.out +++ ql/src/test/results/clientpositive/llap/schema_evol_text_nonvec_part.q.out @@ -53,25 +53,49 @@ POSTHOOK: Lineage: part_add_int_permute_select PARTITION(part=1).b SIMPLE [(valu POSTHOOK: Lineage: part_add_int_permute_select PARTITION(part=1).c EXPRESSION [(values__tmp__table__2)values__tmp__table__2.FieldSchema(name:tmp_values_col4, type:string, comment:), ] POSTHOOK: Lineage: part_add_int_permute_select PARTITION(part=1).insert_num EXPRESSION [(values__tmp__table__2)values__tmp__table__2.FieldSchema(name:tmp_values_col1, type:string, comment:), ] _col0 _col1 _col2 _col3 -PREHOOK: query: explain +PREHOOK: query: explain vectorization detail select insert_num,part,a,b from part_add_int_permute_select PREHOOK: type: QUERY -POSTHOOK: query: explain +POSTHOOK: query: explain vectorization detail select insert_num,part,a,b from part_add_int_permute_select POSTHOOK: type: QUERY Explain -Plan optimized by CBO. +PLAN VECTORIZATION: + enabled: false + enabledConditionsNotMet: [hive.vectorized.execution.enabled IS false] -Stage-0 - Fetch Operator - limit:-1 - Stage-1 - Map 1 llap - File Output Operator [FS_2] - Select Operator [SEL_1] (rows=2 width=4) - Output:["_col0","_col1","_col2","_col3"] - TableScan [TS_0] (rows=2 width=16) - default@part_add_int_permute_select,part_add_int_permute_select,Tbl:COMPLETE,Col:PARTIAL,Output:["insert_num","a","b"] +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: part_add_int_permute_select + Statistics: Num rows: 2 Data size: 33 Basic stats: COMPLETE Column stats: PARTIAL + Select Operator + expressions: insert_num (type: int), part (type: int), a (type: int), b (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: PARTIAL + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: PARTIAL + 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 + Execution mode: llap + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink PREHOOK: query: select insert_num,part,a,b from part_add_int_permute_select PREHOOK: type: QUERY @@ -158,25 +182,49 @@ POSTHOOK: Lineage: part_add_int_string_permute_select PARTITION(part=1).c EXPRES POSTHOOK: Lineage: part_add_int_string_permute_select PARTITION(part=1).d SIMPLE [(values__tmp__table__4)values__tmp__table__4.FieldSchema(name:tmp_values_col5, type:string, comment:), ] POSTHOOK: Lineage: part_add_int_string_permute_select PARTITION(part=1).insert_num EXPRESSION [(values__tmp__table__4)values__tmp__table__4.FieldSchema(name:tmp_values_col1, type:string, comment:), ] _col0 _col1 _col2 _col3 _col4 -PREHOOK: query: explain +PREHOOK: query: explain vectorization detail select insert_num,part,a,b from part_add_int_string_permute_select PREHOOK: type: QUERY -POSTHOOK: query: explain +POSTHOOK: query: explain vectorization detail select insert_num,part,a,b from part_add_int_string_permute_select POSTHOOK: type: QUERY Explain -Plan optimized by CBO. +PLAN VECTORIZATION: + enabled: false + enabledConditionsNotMet: [hive.vectorized.execution.enabled IS false] -Stage-0 - Fetch Operator - limit:-1 - Stage-1 - Map 1 llap - File Output Operator [FS_2] - Select Operator [SEL_1] (rows=2 width=4) - Output:["_col0","_col1","_col2","_col3"] - TableScan [TS_0] (rows=2 width=19) - default@part_add_int_string_permute_select,part_add_int_string_permute_select,Tbl:COMPLETE,Col:PARTIAL,Output:["insert_num","a","b"] +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: part_add_int_string_permute_select + Statistics: Num rows: 2 Data size: 38 Basic stats: COMPLETE Column stats: PARTIAL + Select Operator + expressions: insert_num (type: int), part (type: int), a (type: int), b (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: PARTIAL + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: PARTIAL + 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 + Execution mode: llap + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink PREHOOK: query: select insert_num,part,a,b from part_add_int_string_permute_select PREHOOK: type: QUERY @@ -321,25 +369,49 @@ POSTHOOK: Lineage: part_change_string_group_double PARTITION(part=1).c2 SIMPLE [ POSTHOOK: Lineage: part_change_string_group_double PARTITION(part=1).c3 SIMPLE [(schema_evolution_data)schema_evolution_data.FieldSchema(name:double1, type:double, comment:null), ] POSTHOOK: Lineage: part_change_string_group_double PARTITION(part=1).insert_num SIMPLE [(schema_evolution_data)schema_evolution_data.FieldSchema(name:insert_num, type:int, comment:null), ] insert_num double1 double1 double1 _c4 -PREHOOK: query: explain +PREHOOK: query: explain vectorization detail select insert_num,part,c1,c2,c3,b from part_change_string_group_double PREHOOK: type: QUERY -POSTHOOK: query: explain +POSTHOOK: query: explain vectorization detail select insert_num,part,c1,c2,c3,b from part_change_string_group_double POSTHOOK: type: QUERY Explain -Plan optimized by CBO. +PLAN VECTORIZATION: + enabled: false + enabledConditionsNotMet: [hive.vectorized.execution.enabled IS false] + +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 -Stage-0 - Fetch Operator - limit:-1 - Stage-1 - Map 1 llap - File Output Operator [FS_2] - Select Operator [SEL_1] (rows=5 width=4) - Output:["_col0","_col1","_col2","_col3","_col4","_col5"] - TableScan [TS_0] (rows=5 width=94) - default@part_change_string_group_double,part_change_string_group_double,Tbl:COMPLETE,Col:PARTIAL,Output:["insert_num","c1","c2","c3","b"] +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: part_change_string_group_double + Statistics: Num rows: 5 Data size: 471 Basic stats: COMPLETE Column stats: PARTIAL + Select Operator + expressions: insert_num (type: int), part (type: int), c1 (type: double), c2 (type: double), c3 (type: double), b (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: PARTIAL + File Output Operator + compressed: false + Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: PARTIAL + 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 + Execution mode: llap + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink PREHOOK: query: select insert_num,part,c1,c2,c3,b from part_change_string_group_double PREHOOK: type: QUERY @@ -421,25 +493,49 @@ POSTHOOK: Lineage: part_change_date_group_string_group_date_timestamp PARTITION( POSTHOOK: Lineage: part_change_date_group_string_group_date_timestamp PARTITION(part=1).c9 EXPRESSION [(values__tmp__table__5)values__tmp__table__5.FieldSchema(name:tmp_values_col10, type:string, comment:), ] POSTHOOK: Lineage: part_change_date_group_string_group_date_timestamp PARTITION(part=1).insert_num EXPRESSION [(values__tmp__table__5)values__tmp__table__5.FieldSchema(name:tmp_values_col1, type:string, comment:), ] _col0 _col1 _col2 _col3 _col4 _col5 _col6 _col7 _col8 _col9 _col10 _col11 -PREHOOK: query: explain +PREHOOK: query: explain vectorization detail select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,b from part_change_date_group_string_group_date_timestamp PREHOOK: type: QUERY -POSTHOOK: query: explain +POSTHOOK: query: explain vectorization detail select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,b from part_change_date_group_string_group_date_timestamp POSTHOOK: type: QUERY Explain -Plan optimized by CBO. +PLAN VECTORIZATION: + enabled: false + enabledConditionsNotMet: [hive.vectorized.execution.enabled IS false] -Stage-0 - Fetch Operator - limit:-1 - Stage-1 - Map 1 llap - File Output Operator [FS_2] - Select Operator [SEL_1] (rows=6 width=4) - Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12"] - TableScan [TS_0] (rows=6 width=172) - default@part_change_date_group_string_group_date_timestamp,part_change_date_group_string_group_date_timestamp,Tbl:COMPLETE,Col:PARTIAL,Output:["insert_num","c1","c2","c3","c4","c5","c6","c7","c8","c9","c10","b"] +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: part_change_date_group_string_group_date_timestamp + Statistics: Num rows: 6 Data size: 1032 Basic stats: COMPLETE Column stats: PARTIAL + Select Operator + expressions: insert_num (type: int), part (type: int), c1 (type: string), c2 (type: char(50)), c3 (type: char(15)), c4 (type: varchar(50)), c5 (type: varchar(15)), c6 (type: string), c7 (type: char(50)), c8 (type: char(15)), c9 (type: varchar(50)), c10 (type: varchar(15)), b (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 + Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL + File Output Operator + compressed: false + Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL + 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 + Execution mode: llap + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink PREHOOK: query: select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,b from part_change_date_group_string_group_date_timestamp PREHOOK: type: QUERY @@ -590,25 +686,49 @@ POSTHOOK: Lineage: part_change_numeric_group_string_group_multi_ints_string_grou POSTHOOK: Lineage: part_change_numeric_group_string_group_multi_ints_string_group PARTITION(part=1).c9 EXPRESSION [(values__tmp__table__6)values__tmp__table__6.FieldSchema(name:tmp_values_col10, type:string, comment:), ] POSTHOOK: Lineage: part_change_numeric_group_string_group_multi_ints_string_group PARTITION(part=1).insert_num EXPRESSION [(values__tmp__table__6)values__tmp__table__6.FieldSchema(name:tmp_values_col1, type:string, comment:), ] _col0 _col1 _col2 _col3 _col4 _col5 _col6 _col7 _col8 _col9 _col10 _col11 _col12 _col13 _col14 _col15 _col16 _col17 _col18 _col19 _col20 _col21 -PREHOOK: query: explain +PREHOOK: query: explain vectorization detail select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,c16,c17,c18,c19,c20,b from part_change_numeric_group_string_group_multi_ints_string_group PREHOOK: type: QUERY -POSTHOOK: query: explain +POSTHOOK: query: explain vectorization detail select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,c16,c17,c18,c19,c20,b from part_change_numeric_group_string_group_multi_ints_string_group POSTHOOK: type: QUERY Explain -Plan optimized by CBO. +PLAN VECTORIZATION: + enabled: false + enabledConditionsNotMet: [hive.vectorized.execution.enabled IS false] + +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 -Stage-0 - Fetch Operator - limit:-1 - Stage-1 - Map 1 llap - File Output Operator [FS_2] - Select Operator [SEL_1] (rows=6 width=4) - Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17","_col18","_col19","_col20","_col21","_col22"] - TableScan [TS_0] (rows=6 width=182) - default@part_change_numeric_group_string_group_multi_ints_string_group,part_change_numeric_group_string_group_multi_ints_string_group,Tbl:COMPLETE,Col:PARTIAL,Output:["insert_num","c1","c2","c3","c4","c5","c6","c7","c8","c9","c10","c11","c12","c13","c14","c15","c16","c17","c18","c19","c20","b"] +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: part_change_numeric_group_string_group_multi_ints_string_group + Statistics: Num rows: 6 Data size: 1094 Basic stats: COMPLETE Column stats: PARTIAL + Select Operator + expressions: insert_num (type: int), part (type: int), c1 (type: string), c2 (type: string), c3 (type: string), c4 (type: string), c5 (type: char(50)), c6 (type: char(50)), c7 (type: char(50)), c8 (type: char(50)), c9 (type: char(5)), c10 (type: char(5)), c11 (type: char(5)), c12 (type: char(5)), c13 (type: varchar(50)), c14 (type: varchar(50)), c15 (type: varchar(50)), c16 (type: varchar(50)), c17 (type: varchar(5)), c18 (type: varchar(5)), c19 (type: varchar(5)), c20 (type: varchar(5)), b (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22 + Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL + File Output Operator + compressed: false + Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL + 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 + Execution mode: llap + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink PREHOOK: query: select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,c16,c17,c18,c19,c20,b from part_change_numeric_group_string_group_multi_ints_string_group PREHOOK: type: QUERY @@ -749,25 +869,49 @@ POSTHOOK: Lineage: part_change_numeric_group_string_group_floating_string_group POSTHOOK: Lineage: part_change_numeric_group_string_group_floating_string_group PARTITION(part=1).c9 EXPRESSION [(values__tmp__table__7)values__tmp__table__7.FieldSchema(name:tmp_values_col10, type:string, comment:), ] POSTHOOK: Lineage: part_change_numeric_group_string_group_floating_string_group PARTITION(part=1).insert_num EXPRESSION [(values__tmp__table__7)values__tmp__table__7.FieldSchema(name:tmp_values_col1, type:string, comment:), ] _col0 _col1 _col2 _col3 _col4 _col5 _col6 _col7 _col8 _col9 _col10 _col11 _col12 _col13 _col14 _col15 _col16 -PREHOOK: query: explain +PREHOOK: query: explain vectorization detail select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,b from part_change_numeric_group_string_group_floating_string_group PREHOOK: type: QUERY -POSTHOOK: query: explain +POSTHOOK: query: explain vectorization detail select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,b from part_change_numeric_group_string_group_floating_string_group POSTHOOK: type: QUERY Explain -Plan optimized by CBO. +PLAN VECTORIZATION: + enabled: false + enabledConditionsNotMet: [hive.vectorized.execution.enabled IS false] + +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: part_change_numeric_group_string_group_floating_string_group + Statistics: Num rows: 6 Data size: 1521 Basic stats: COMPLETE Column stats: PARTIAL + Select Operator + expressions: insert_num (type: int), part (type: int), c1 (type: string), c2 (type: string), c3 (type: string), c4 (type: char(50)), c5 (type: char(50)), c6 (type: char(50)), c7 (type: char(7)), c8 (type: char(7)), c9 (type: char(7)), c10 (type: varchar(50)), c11 (type: varchar(50)), c12 (type: varchar(50)), c13 (type: varchar(7)), c14 (type: varchar(7)), c15 (type: varchar(7)), b (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17 + Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL + File Output Operator + compressed: false + Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL + 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 + Execution mode: llap -Stage-0 - Fetch Operator - limit:-1 - Stage-1 - Map 1 llap - File Output Operator [FS_2] - Select Operator [SEL_1] (rows=6 width=4) - Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17"] - TableScan [TS_0] (rows=6 width=253) - default@part_change_numeric_group_string_group_floating_string_group,part_change_numeric_group_string_group_floating_string_group,Tbl:COMPLETE,Col:PARTIAL,Output:["insert_num","c1","c2","c3","c4","c5","c6","c7","c8","c9","c10","c11","c12","c13","c14","c15","b"] + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink PREHOOK: query: select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,b from part_change_numeric_group_string_group_floating_string_group PREHOOK: type: QUERY @@ -894,25 +1038,49 @@ POSTHOOK: Lineage: part_change_string_group_string_group_string PARTITION(part=1 POSTHOOK: Lineage: part_change_string_group_string_group_string PARTITION(part=1).c9 EXPRESSION [(values__tmp__table__8)values__tmp__table__8.FieldSchema(name:tmp_values_col10, type:string, comment:), ] POSTHOOK: Lineage: part_change_string_group_string_group_string PARTITION(part=1).insert_num EXPRESSION [(values__tmp__table__8)values__tmp__table__8.FieldSchema(name:tmp_values_col1, type:string, comment:), ] _col0 _col1 _col2 _col3 _col4 _col5 _col6 _col7 _col8 _col9 _col10 _col11 -PREHOOK: query: explain +PREHOOK: query: explain vectorization detail select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,b from part_change_string_group_string_group_string PREHOOK: type: QUERY -POSTHOOK: query: explain +POSTHOOK: query: explain vectorization detail select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,b from part_change_string_group_string_group_string POSTHOOK: type: QUERY Explain -Plan optimized by CBO. +PLAN VECTORIZATION: + enabled: false + enabledConditionsNotMet: [hive.vectorized.execution.enabled IS false] + +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: part_change_string_group_string_group_string + Statistics: Num rows: 6 Data size: 1205 Basic stats: COMPLETE Column stats: PARTIAL + Select Operator + expressions: insert_num (type: int), part (type: int), c1 (type: char(50)), c2 (type: char(9)), c3 (type: varchar(50)), c4 (type: char(9)), c5 (type: varchar(50)), c6 (type: varchar(9)), c7 (type: string), c8 (type: char(50)), c9 (type: char(9)), c10 (type: string), b (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 + Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL + File Output Operator + compressed: false + Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL + 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 + Execution mode: llap -Stage-0 - Fetch Operator - limit:-1 - Stage-1 - Map 1 llap - File Output Operator [FS_2] - Select Operator [SEL_1] (rows=6 width=4) - Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12"] - TableScan [TS_0] (rows=6 width=200) - default@part_change_string_group_string_group_string,part_change_string_group_string_group_string,Tbl:COMPLETE,Col:PARTIAL,Output:["insert_num","c1","c2","c3","c4","c5","c6","c7","c8","c9","c10","b"] + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink PREHOOK: query: select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,b from part_change_string_group_string_group_string PREHOOK: type: QUERY @@ -1067,25 +1235,49 @@ POSTHOOK: Lineage: part_change_lower_to_higher_numeric_group_tinyint_to_bigint P POSTHOOK: Lineage: part_change_lower_to_higher_numeric_group_tinyint_to_bigint PARTITION(part=1).c9 EXPRESSION [(values__tmp__table__9)values__tmp__table__9.FieldSchema(name:tmp_values_col10, type:string, comment:), ] POSTHOOK: Lineage: part_change_lower_to_higher_numeric_group_tinyint_to_bigint PARTITION(part=1).insert_num EXPRESSION [(values__tmp__table__9)values__tmp__table__9.FieldSchema(name:tmp_values_col1, type:string, comment:), ] _col0 _col1 _col2 _col3 _col4 _col5 _col6 _col7 _col8 _col9 _col10 _col11 _col12 _col13 _col14 _col15 _col16 _col17 _col18 _col19 -PREHOOK: query: explain +PREHOOK: query: explain vectorization detail select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,c16,c17,c18,b from part_change_lower_to_higher_numeric_group_tinyint_to_bigint PREHOOK: type: QUERY -POSTHOOK: query: explain +POSTHOOK: query: explain vectorization detail select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,c16,c17,c18,b from part_change_lower_to_higher_numeric_group_tinyint_to_bigint POSTHOOK: type: QUERY Explain -Plan optimized by CBO. +PLAN VECTORIZATION: + enabled: false + enabledConditionsNotMet: [hive.vectorized.execution.enabled IS false] -Stage-0 - Fetch Operator - limit:-1 - Stage-1 - Map 1 llap - File Output Operator [FS_2] - Select Operator [SEL_1] (rows=6 width=4) - Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17","_col18","_col19","_col20"] - TableScan [TS_0] (rows=6 width=143) - default@part_change_lower_to_higher_numeric_group_tinyint_to_bigint,part_change_lower_to_higher_numeric_group_tinyint_to_bigint,Tbl:COMPLETE,Col:PARTIAL,Output:["insert_num","c1","c2","c3","c4","c5","c6","c7","c8","c9","c10","c11","c12","c13","c14","c15","c16","c17","c18","b"] +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: part_change_lower_to_higher_numeric_group_tinyint_to_bigint + Statistics: Num rows: 6 Data size: 860 Basic stats: COMPLETE Column stats: PARTIAL + Select Operator + expressions: insert_num (type: int), part (type: int), c1 (type: smallint), c2 (type: int), c3 (type: bigint), c4 (type: decimal(38,18)), c5 (type: float), c6 (type: double), c7 (type: int), c8 (type: bigint), c9 (type: decimal(38,18)), c10 (type: float), c11 (type: double), c12 (type: bigint), c13 (type: decimal(38,18)), c14 (type: float), c15 (type: double), c16 (type: decimal(38,18)), c17 (type: float), c18 (type: double), b (type: string) + 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: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL + File Output Operator + compressed: false + Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL + 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 + Execution mode: llap + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink PREHOOK: query: select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,c16,c17,c18,b from part_change_lower_to_higher_numeric_group_tinyint_to_bigint PREHOOK: type: QUERY @@ -1182,25 +1374,49 @@ POSTHOOK: Lineage: part_change_lower_to_higher_numeric_group_decimal_to_float PA POSTHOOK: Lineage: part_change_lower_to_higher_numeric_group_decimal_to_float PARTITION(part=1).c3 EXPRESSION [(values__tmp__table__10)values__tmp__table__10.FieldSchema(name:tmp_values_col4, type:string, comment:), ] POSTHOOK: Lineage: part_change_lower_to_higher_numeric_group_decimal_to_float PARTITION(part=1).insert_num EXPRESSION [(values__tmp__table__10)values__tmp__table__10.FieldSchema(name:tmp_values_col1, type:string, comment:), ] _col0 _col1 _col2 _col3 _col4 -PREHOOK: query: explain +PREHOOK: query: explain vectorization detail select insert_num,part,c1,c2,c3,b from part_change_lower_to_higher_numeric_group_decimal_to_float PREHOOK: type: QUERY -POSTHOOK: query: explain +POSTHOOK: query: explain vectorization detail select insert_num,part,c1,c2,c3,b from part_change_lower_to_higher_numeric_group_decimal_to_float POSTHOOK: type: QUERY Explain -Plan optimized by CBO. +PLAN VECTORIZATION: + enabled: false + enabledConditionsNotMet: [hive.vectorized.execution.enabled IS false] + +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: part_change_lower_to_higher_numeric_group_decimal_to_float + Statistics: Num rows: 6 Data size: 428 Basic stats: COMPLETE Column stats: PARTIAL + Select Operator + expressions: insert_num (type: int), part (type: int), c1 (type: float), c2 (type: double), c3 (type: double), b (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL + File Output Operator + compressed: false + Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL + 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 + Execution mode: llap -Stage-0 - Fetch Operator - limit:-1 - Stage-1 - Map 1 llap - File Output Operator [FS_2] - Select Operator [SEL_1] (rows=6 width=4) - Output:["_col0","_col1","_col2","_col3","_col4","_col5"] - TableScan [TS_0] (rows=6 width=71) - default@part_change_lower_to_higher_numeric_group_decimal_to_float,part_change_lower_to_higher_numeric_group_decimal_to_float,Tbl:COMPLETE,Col:PARTIAL,Output:["insert_num","c1","c2","c3","b"] + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink PREHOOK: query: select insert_num,part,c1,c2,c3,b from part_change_lower_to_higher_numeric_group_decimal_to_float PREHOOK: type: QUERY diff --git ql/src/test/results/clientpositive/llap/schema_evol_text_nonvec_part_all_complex.q.out ql/src/test/results/clientpositive/llap/schema_evol_text_nonvec_part_all_complex.q.out index be42c05..12c7db4 100644 --- ql/src/test/results/clientpositive/llap/schema_evol_text_nonvec_part_all_complex.q.out +++ ql/src/test/results/clientpositive/llap/schema_evol_text_nonvec_part_all_complex.q.out @@ -131,25 +131,49 @@ POSTHOOK: Lineage: part_change_various_various_struct1 PARTITION(part=1).b SIMPL POSTHOOK: Lineage: part_change_various_various_struct1 PARTITION(part=1).insert_num SIMPLE [(complex_struct1_c_txt)complex_struct1_c_txt.FieldSchema(name:insert_num, type:int, comment:null), ] POSTHOOK: Lineage: part_change_various_various_struct1 PARTITION(part=1).s1 SIMPLE [(complex_struct1_c_txt)complex_struct1_c_txt.FieldSchema(name:s1, type:struct, comment:null), ] complex_struct1_c_txt.insert_num complex_struct1_c_txt.s1 complex_struct1_c_txt.b -PREHOOK: query: explain +PREHOOK: query: explain vectorization detail select insert_num,part,s1,b from part_change_various_various_struct1 PREHOOK: type: QUERY -POSTHOOK: query: explain +POSTHOOK: query: explain vectorization detail select insert_num,part,s1,b from part_change_various_various_struct1 POSTHOOK: type: QUERY Explain -Plan optimized by CBO. +PLAN VECTORIZATION: + enabled: false + enabledConditionsNotMet: [hive.vectorized.execution.enabled IS false] -Stage-0 - Fetch Operator - limit:-1 - Stage-1 - Map 1 llap - File Output Operator [FS_2] - Select Operator [SEL_1] (rows=6 width=4) - Output:["_col0","_col1","_col2","_col3"] - TableScan [TS_0] (rows=6 width=155) - default@part_change_various_various_struct1,part_change_various_various_struct1,Tbl:COMPLETE,Col:PARTIAL,Output:["insert_num","s1","b"] +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: part_change_various_various_struct1 + Statistics: Num rows: 6 Data size: 931 Basic stats: COMPLETE Column stats: PARTIAL + Select Operator + expressions: insert_num (type: int), part (type: int), s1 (type: struct), b (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL + File Output Operator + compressed: false + Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL + 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 + Execution mode: llap + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink PREHOOK: query: select insert_num,part,s1,b from part_change_various_various_struct1 PREHOOK: type: QUERY @@ -383,25 +407,49 @@ POSTHOOK: Lineage: part_add_various_various_struct2 PARTITION(part=1).b SIMPLE [ POSTHOOK: Lineage: part_add_various_various_struct2 PARTITION(part=1).insert_num SIMPLE [(complex_struct2_d_txt)complex_struct2_d_txt.FieldSchema(name:insert_num, type:int, comment:null), ] POSTHOOK: Lineage: part_add_various_various_struct2 PARTITION(part=1).s2 SIMPLE [(complex_struct2_d_txt)complex_struct2_d_txt.FieldSchema(name:s2, type:struct, comment:null), ] complex_struct2_d_txt.insert_num complex_struct2_d_txt.b complex_struct2_d_txt.s2 -PREHOOK: query: explain +PREHOOK: query: explain vectorization detail select insert_num,part,b,s2 from part_add_various_various_struct2 PREHOOK: type: QUERY -POSTHOOK: query: explain +POSTHOOK: query: explain vectorization detail select insert_num,part,b,s2 from part_add_various_various_struct2 POSTHOOK: type: QUERY Explain -Plan optimized by CBO. +PLAN VECTORIZATION: + enabled: false + enabledConditionsNotMet: [hive.vectorized.execution.enabled IS false] + +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 -Stage-0 - Fetch Operator - limit:-1 - Stage-1 - Map 1 llap - File Output Operator [FS_2] - Select Operator [SEL_1] (rows=8 width=4) - Output:["_col0","_col1","_col2","_col3"] - TableScan [TS_0] (rows=8 width=117) - default@part_add_various_various_struct2,part_add_various_various_struct2,Tbl:COMPLETE,Col:PARTIAL,Output:["insert_num","b","s2"] +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: part_add_various_various_struct2 + Statistics: Num rows: 8 Data size: 939 Basic stats: COMPLETE Column stats: PARTIAL + Select Operator + expressions: insert_num (type: int), part (type: int), b (type: string), s2 (type: struct) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 8 Data size: 32 Basic stats: COMPLETE Column stats: PARTIAL + File Output Operator + compressed: false + Statistics: Num rows: 8 Data size: 32 Basic stats: COMPLETE Column stats: PARTIAL + 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 + Execution mode: llap + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink PREHOOK: query: select insert_num,part,b,s2 from part_add_various_various_struct2 PREHOOK: type: QUERY @@ -563,25 +611,49 @@ POSTHOOK: Lineage: part_add_to_various_various_struct4 PARTITION(part=1).b SIMPL POSTHOOK: Lineage: part_add_to_various_various_struct4 PARTITION(part=1).insert_num SIMPLE [(complex_struct4_c_txt)complex_struct4_c_txt.FieldSchema(name:insert_num, type:int, comment:null), ] POSTHOOK: Lineage: part_add_to_various_various_struct4 PARTITION(part=1).s3 SIMPLE [(complex_struct4_c_txt)complex_struct4_c_txt.FieldSchema(name:s3, type:struct, comment:null), ] complex_struct4_c_txt.insert_num complex_struct4_c_txt.b complex_struct4_c_txt.s3 -PREHOOK: query: explain +PREHOOK: query: explain vectorization detail select insert_num,part,b,s3 from part_add_to_various_various_struct4 PREHOOK: type: QUERY -POSTHOOK: query: explain +POSTHOOK: query: explain vectorization detail select insert_num,part,b,s3 from part_add_to_various_various_struct4 POSTHOOK: type: QUERY Explain -Plan optimized by CBO. +PLAN VECTORIZATION: + enabled: false + enabledConditionsNotMet: [hive.vectorized.execution.enabled IS false] + +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: part_add_to_various_various_struct4 + Statistics: Num rows: 4 Data size: 353 Basic stats: COMPLETE Column stats: PARTIAL + Select Operator + expressions: insert_num (type: int), part (type: int), b (type: string), s3 (type: struct) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: PARTIAL + File Output Operator + compressed: false + Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: PARTIAL + 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 + Execution mode: llap -Stage-0 - Fetch Operator - limit:-1 - Stage-1 - Map 1 llap - File Output Operator [FS_2] - Select Operator [SEL_1] (rows=4 width=4) - Output:["_col0","_col1","_col2","_col3"] - TableScan [TS_0] (rows=4 width=88) - default@part_add_to_various_various_struct4,part_add_to_various_various_struct4,Tbl:COMPLETE,Col:PARTIAL,Output:["insert_num","b","s3"] + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink PREHOOK: query: select insert_num,part,b,s3 from part_add_to_various_various_struct4 PREHOOK: type: QUERY diff --git ql/src/test/results/clientpositive/llap/schema_evol_text_nonvec_part_all_primitive.q.out ql/src/test/results/clientpositive/llap/schema_evol_text_nonvec_part_all_primitive.q.out index 03c6936..757ea3a 100644 --- ql/src/test/results/clientpositive/llap/schema_evol_text_nonvec_part_all_primitive.q.out +++ ql/src/test/results/clientpositive/llap/schema_evol_text_nonvec_part_all_primitive.q.out @@ -242,25 +242,49 @@ POSTHOOK: Lineage: part_change_various_various_boolean_to_bigint PARTITION(part= POSTHOOK: Lineage: part_change_various_various_boolean_to_bigint PARTITION(part=1).c9 SIMPLE [(schema_evolution_data)schema_evolution_data.FieldSchema(name:boolean1, type:boolean, comment:null), ] POSTHOOK: Lineage: part_change_various_various_boolean_to_bigint PARTITION(part=1).insert_num SIMPLE [(schema_evolution_data)schema_evolution_data.FieldSchema(name:insert_num, type:int, comment:null), ] insert_num boolean1 boolean1 boolean1 boolean1 boolean1 boolean1 boolean1 boolean1 boolean1 tinyint1 tinyint1 tinyint1 tinyint1 tinyint1 tinyint1 tinyint1 tinyint1 tinyint1 tinyint1 tinyint1 smallint1 smallint1 smallint1 smallint1 smallint1 smallint1 smallint1 smallint1 smallint1 smallint1 smallint1 int1 int1 int1 int1 int1 int1 int1 int1 int1 int1 int1 bigint1 bigint1 bigint1 bigint1 bigint1 bigint1 bigint1 bigint1 bigint1 bigint1 bigint1 _c54 -PREHOOK: query: explain +PREHOOK: query: explain vectorization detail select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,c16,c17,c18,c19,c20,c21,c22,c23,c24,c25,c26,c27,c28,c29,c30,c31,c32,c33,c34,c35,c36,c37,c38,c39,c40,c41,c42,c43,c44,c45,c46,c47,c48,c49,c50,c51,c52,c53,b from part_change_various_various_boolean_to_bigint PREHOOK: type: QUERY -POSTHOOK: query: explain +POSTHOOK: query: explain vectorization detail select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,c16,c17,c18,c19,c20,c21,c22,c23,c24,c25,c26,c27,c28,c29,c30,c31,c32,c33,c34,c35,c36,c37,c38,c39,c40,c41,c42,c43,c44,c45,c46,c47,c48,c49,c50,c51,c52,c53,b from part_change_various_various_boolean_to_bigint POSTHOOK: type: QUERY Explain -Plan optimized by CBO. +PLAN VECTORIZATION: + enabled: false + enabledConditionsNotMet: [hive.vectorized.execution.enabled IS false] -Stage-0 - Fetch Operator - limit:-1 - Stage-1 - Map 1 llap - File Output Operator [FS_2] - Select Operator [SEL_1] (rows=10 width=4) - Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17","_col18","_col19","_col20","_col21","_col22","_col23","_col24","_col25","_col26","_col27","_col28","_col29","_col30","_col31","_col32","_col33","_col34","_col35","_col36","_col37","_col38","_col39","_col40","_col41","_col42","_col43","_col44","_col45","_col46","_col47","_col48","_col49","_col50","_col51","_col52","_col53","_col54","_col55"] - TableScan [TS_0] (rows=10 width=512) - default@part_change_various_various_boolean_to_bigint,part_change_various_various_boolean_to_bigint,Tbl:COMPLETE,Col:PARTIAL,Output:["insert_num","c1","c2","c3","c4","c5","c6","c7","c8","c9","c10","c11","c12","c13","c14","c15","c16","c17","c18","c19","c20","c21","c22","c23","c24","c25","c26","c27","c28","c29","c30","c31","c32","c33","c34","c35","c36","c37","c38","c39","c40","c41","c42","c43","c44","c45","c46","c47","c48","c49","c50","c51","c52","c53","b"] +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: part_change_various_various_boolean_to_bigint + Statistics: Num rows: 10 Data size: 5126 Basic stats: COMPLETE Column stats: PARTIAL + Select Operator + expressions: insert_num (type: int), part (type: int), c1 (type: boolean), c2 (type: boolean), c3 (type: boolean), c4 (type: boolean), c5 (type: boolean), c6 (type: boolean), c7 (type: boolean), c8 (type: boolean), c9 (type: boolean), c10 (type: tinyint), c11 (type: tinyint), c12 (type: tinyint), c13 (type: tinyint), c14 (type: tinyint), c15 (type: tinyint), c16 (type: tinyint), c17 (type: tinyint), c18 (type: tinyint), c19 (type: tinyint), c20 (type: tinyint), c21 (type: smallint), c22 (type: smallint), c23 (type: smallint), c24 (type: smallint), c25 (type: smallint), c26 (type: smallint), c27 (type: smallint), c28 (type: smallint), c29 (type: smallint), c30 (type: smallint), c31 (type: smallint), c32 (type: int), c33 (type: int), c34 (type: int), c35 (type: int), c36 (type: int), c37 (type: int), c38 (type: int), c39 (type: int), c40 (type: int), c41 (type: int), c42 (type: int), c43 (type: bigint), c44 (type: bigint), c45 (type: bigint), c46 (type: bigint), c47 (type: bigint), c48 (type: bigint), c49 (type: bigint), c50 (type: bigint), c51 (type: bigint), c52 (type: bigint), c53 (type: bigint), b (type: string) + 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, _col24, _col25, _col26, _col27, _col28, _col29, _col30, _col31, _col32, _col33, _col34, _col35, _col36, _col37, _col38, _col39, _col40, _col41, _col42, _col43, _col44, _col45, _col46, _col47, _col48, _col49, _col50, _col51, _col52, _col53, _col54, _col55 + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: PARTIAL + File Output Operator + compressed: false + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: PARTIAL + 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 + Execution mode: llap + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink PREHOOK: query: select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,c16,c17,c18,c19,c20,c21,c22,c23,c24,c25,c26,c27,c28,c29,c30,c31,c32,c33,c34,c35,c36,c37,c38,c39,c40,c41,c42,c43,c44,c45,c46,c47,c48,c49,c50,c51,c52,c53,b from part_change_various_various_boolean_to_bigint PREHOOK: type: QUERY @@ -443,25 +467,49 @@ POSTHOOK: Lineage: part_change_various_various_decimal_to_double PARTITION(part= POSTHOOK: Lineage: part_change_various_various_decimal_to_double PARTITION(part=1).c9 SIMPLE [(schema_evolution_data_2)schema_evolution_data_2.FieldSchema(name:decimal1, type:decimal(38,18), comment:null), ] POSTHOOK: Lineage: part_change_various_various_decimal_to_double PARTITION(part=1).insert_num SIMPLE [(schema_evolution_data_2)schema_evolution_data_2.FieldSchema(name:insert_num, type:int, comment:null), ] insert_num decimal1 decimal1 decimal1 decimal1 decimal1 decimal1 decimal1 decimal1 decimal1 decimal1 decimal1 float1 float1 float1 float1 float1 float1 float1 float1 float1 float1 float1 double1 double1 double1 double1 double1 double1 double1 double1 double1 double1 double1 _c34 -PREHOOK: query: explain +PREHOOK: query: explain vectorization detail select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,c16,c17,c18,c19,c20,c21,c22,c23,c24,c25,c26,c27,c28,c29,c30,c31,c32,c33,b from part_change_various_various_decimal_to_double PREHOOK: type: QUERY -POSTHOOK: query: explain +POSTHOOK: query: explain vectorization detail select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,c16,c17,c18,c19,c20,c21,c22,c23,c24,c25,c26,c27,c28,c29,c30,c31,c32,c33,b from part_change_various_various_decimal_to_double POSTHOOK: type: QUERY Explain -Plan optimized by CBO. +PLAN VECTORIZATION: + enabled: false + enabledConditionsNotMet: [hive.vectorized.execution.enabled IS false] + +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 -Stage-0 - Fetch Operator - limit:-1 - Stage-1 - Map 1 llap - File Output Operator [FS_2] - Select Operator [SEL_1] (rows=6 width=4) - Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17","_col18","_col19","_col20","_col21","_col22","_col23","_col24","_col25","_col26","_col27","_col28","_col29","_col30","_col31","_col32","_col33","_col34","_col35"] - TableScan [TS_0] (rows=6 width=455) - default@part_change_various_various_decimal_to_double,part_change_various_various_decimal_to_double,Tbl:COMPLETE,Col:PARTIAL,Output:["insert_num","c1","c2","c3","c4","c5","c6","c7","c8","c9","c10","c11","c12","c13","c14","c15","c16","c17","c18","c19","c20","c21","c22","c23","c24","c25","c26","c27","c28","c29","c30","c31","c32","c33","b"] +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: part_change_various_various_decimal_to_double + Statistics: Num rows: 6 Data size: 2735 Basic stats: COMPLETE Column stats: PARTIAL + Select Operator + expressions: insert_num (type: int), part (type: int), c1 (type: decimal(38,18)), c2 (type: decimal(38,18)), c3 (type: decimal(38,18)), c4 (type: decimal(38,18)), c5 (type: decimal(38,18)), c6 (type: decimal(38,18)), c7 (type: decimal(38,18)), c8 (type: decimal(38,18)), c9 (type: decimal(38,18)), c10 (type: decimal(38,18)), c11 (type: decimal(38,18)), c12 (type: float), c13 (type: float), c14 (type: float), c15 (type: float), c16 (type: float), c17 (type: float), c18 (type: float), c19 (type: float), c20 (type: float), c21 (type: float), c22 (type: float), c23 (type: double), c24 (type: double), c25 (type: double), c26 (type: double), c27 (type: double), c28 (type: double), c29 (type: double), c30 (type: double), c31 (type: double), c32 (type: double), c33 (type: double), b (type: string) + 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, _col24, _col25, _col26, _col27, _col28, _col29, _col30, _col31, _col32, _col33, _col34, _col35 + Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL + File Output Operator + compressed: false + Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL + 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 + Execution mode: llap + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink PREHOOK: query: select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,c16,c17,c18,c19,c20,c21,c22,c23,c24,c25,c26,c27,c28,c29,c30,c31,c32,c33,b from part_change_various_various_decimal_to_double PREHOOK: type: QUERY @@ -566,25 +614,49 @@ POSTHOOK: Lineage: part_change_various_various_timestamp PARTITION(part=1).c8 SI POSTHOOK: Lineage: part_change_various_various_timestamp PARTITION(part=1).c9 SIMPLE [(schema_evolution_data_2)schema_evolution_data_2.FieldSchema(name:timestamp1, type:timestamp, comment:null), ] POSTHOOK: Lineage: part_change_various_various_timestamp PARTITION(part=1).insert_num SIMPLE [(schema_evolution_data_2)schema_evolution_data_2.FieldSchema(name:insert_num, type:int, comment:null), ] insert_num timestamp1 timestamp1 timestamp1 timestamp1 timestamp1 timestamp1 timestamp1 timestamp1 timestamp1 timestamp1 timestamp1 timestamp1 _c13 -PREHOOK: query: explain +PREHOOK: query: explain vectorization detail select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,b from part_change_various_various_timestamp PREHOOK: type: QUERY -POSTHOOK: query: explain +POSTHOOK: query: explain vectorization detail select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,b from part_change_various_various_timestamp POSTHOOK: type: QUERY Explain -Plan optimized by CBO. +PLAN VECTORIZATION: + enabled: false + enabledConditionsNotMet: [hive.vectorized.execution.enabled IS false] -Stage-0 - Fetch Operator - limit:-1 - Stage-1 - Map 1 llap - File Output Operator [FS_2] - Select Operator [SEL_1] (rows=6 width=4) - Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14"] - TableScan [TS_0] (rows=6 width=151) - default@part_change_various_various_timestamp,part_change_various_various_timestamp,Tbl:COMPLETE,Col:PARTIAL,Output:["insert_num","c1","c2","c3","c4","c5","c6","c7","c8","c9","c10","c11","c12","b"] +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: part_change_various_various_timestamp + Statistics: Num rows: 6 Data size: 907 Basic stats: COMPLETE Column stats: PARTIAL + Select Operator + expressions: insert_num (type: int), part (type: int), c1 (type: timestamp), c2 (type: timestamp), c3 (type: timestamp), c4 (type: timestamp), c5 (type: timestamp), c6 (type: timestamp), c7 (type: timestamp), c8 (type: timestamp), c9 (type: timestamp), c10 (type: timestamp), c11 (type: timestamp), c12 (type: timestamp), b (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14 + Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL + File Output Operator + compressed: false + Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL + 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 + Execution mode: llap + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink PREHOOK: query: select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,b from part_change_various_various_timestamp PREHOOK: type: QUERY @@ -673,25 +745,49 @@ POSTHOOK: Lineage: part_change_various_various_date PARTITION(part=1).c3 SIMPLE POSTHOOK: Lineage: part_change_various_various_date PARTITION(part=1).c4 SIMPLE [(schema_evolution_data_2)schema_evolution_data_2.FieldSchema(name:date1, type:date, comment:null), ] POSTHOOK: Lineage: part_change_various_various_date PARTITION(part=1).insert_num SIMPLE [(schema_evolution_data_2)schema_evolution_data_2.FieldSchema(name:insert_num, type:int, comment:null), ] insert_num date1 date1 date1 date1 _c5 -PREHOOK: query: explain +PREHOOK: query: explain vectorization detail select insert_num,part,c1,c2,c3,c4,b from part_change_various_various_date PREHOOK: type: QUERY -POSTHOOK: query: explain +POSTHOOK: query: explain vectorization detail select insert_num,part,c1,c2,c3,c4,b from part_change_various_various_date POSTHOOK: type: QUERY Explain -Plan optimized by CBO. +PLAN VECTORIZATION: + enabled: false + enabledConditionsNotMet: [hive.vectorized.execution.enabled IS false] + +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: part_change_various_various_date + Statistics: Num rows: 6 Data size: 461 Basic stats: COMPLETE Column stats: PARTIAL + Select Operator + expressions: insert_num (type: int), part (type: int), c1 (type: date), c2 (type: date), c3 (type: date), c4 (type: date), b (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 + Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL + File Output Operator + compressed: false + Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL + 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 + Execution mode: llap -Stage-0 - Fetch Operator - limit:-1 - Stage-1 - Map 1 llap - File Output Operator [FS_2] - Select Operator [SEL_1] (rows=6 width=4) - Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"] - TableScan [TS_0] (rows=6 width=76) - default@part_change_various_various_date,part_change_various_various_date,Tbl:COMPLETE,Col:PARTIAL,Output:["insert_num","c1","c2","c3","c4","b"] + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink PREHOOK: query: select insert_num,part,c1,c2,c3,c4,b from part_change_various_various_date PREHOOK: type: QUERY @@ -861,25 +957,49 @@ POSTHOOK: Lineage: part_change_same_type_different_params PARTITION(part=2).c5 S POSTHOOK: Lineage: part_change_same_type_different_params PARTITION(part=2).c6 SIMPLE [(same_type1_c_txt)same_type1_c_txt.FieldSchema(name:c6, type:decimal(25,15), comment:null), ] POSTHOOK: Lineage: part_change_same_type_different_params PARTITION(part=2).insert_num SIMPLE [(same_type1_c_txt)same_type1_c_txt.FieldSchema(name:insert_num, type:int, comment:null), ] same_type1_c_txt.insert_num same_type1_c_txt.c1 same_type1_c_txt.c2 same_type1_c_txt.c3 same_type1_c_txt.c4 same_type1_c_txt.c5 same_type1_c_txt.c6 same_type1_c_txt.b -PREHOOK: query: explain +PREHOOK: query: explain vectorization detail select insert_num,part,c1,c2,c3,c4,c5,c6,b from part_change_same_type_different_params PREHOOK: type: QUERY -POSTHOOK: query: explain +POSTHOOK: query: explain vectorization detail select insert_num,part,c1,c2,c3,c4,c5,c6,b from part_change_same_type_different_params POSTHOOK: type: QUERY Explain -Plan optimized by CBO. +PLAN VECTORIZATION: + enabled: false + enabledConditionsNotMet: [hive.vectorized.execution.enabled IS false] + +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: part_change_same_type_different_params + Statistics: Num rows: 13 Data size: 1427 Basic stats: COMPLETE Column stats: PARTIAL + Select Operator + expressions: insert_num (type: int), part (type: int), c1 (type: char(8)), c2 (type: char(32)), c3 (type: varchar(15)), c4 (type: varchar(18)), c5 (type: decimal(10,2)), c6 (type: decimal(25,15)), b (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 + Statistics: Num rows: 13 Data size: 52 Basic stats: COMPLETE Column stats: PARTIAL + File Output Operator + compressed: false + Statistics: Num rows: 13 Data size: 52 Basic stats: COMPLETE Column stats: PARTIAL + 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 + Execution mode: llap -Stage-0 - Fetch Operator - limit:-1 - Stage-1 - Map 1 llap - File Output Operator [FS_2] - Select Operator [SEL_1] (rows=13 width=4) - Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"] - TableScan [TS_0] (rows=13 width=109) - default@part_change_same_type_different_params,part_change_same_type_different_params,Tbl:COMPLETE,Col:PARTIAL,Output:["insert_num","c1","c2","c3","c4","c5","c6","b"] + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink PREHOOK: query: select insert_num,part,c1,c2,c3,c4,c5,c6,b from part_change_same_type_different_params PREHOOK: type: QUERY diff --git ql/src/test/results/clientpositive/llap/schema_evol_text_nonvec_table.q.out ql/src/test/results/clientpositive/llap/schema_evol_text_nonvec_table.q.out index da99110..e0a4ffb 100644 --- ql/src/test/results/clientpositive/llap/schema_evol_text_nonvec_table.q.out +++ ql/src/test/results/clientpositive/llap/schema_evol_text_nonvec_table.q.out @@ -55,25 +55,49 @@ POSTHOOK: Lineage: table_add_int_permute_select.b SIMPLE [(values__tmp__table__1 POSTHOOK: Lineage: table_add_int_permute_select.c EXPRESSION [(values__tmp__table__1)values__tmp__table__1.FieldSchema(name:tmp_values_col4, type:string, comment:), ] POSTHOOK: Lineage: table_add_int_permute_select.insert_num EXPRESSION [(values__tmp__table__1)values__tmp__table__1.FieldSchema(name:tmp_values_col1, type:string, comment:), ] _col0 _col1 _col2 _col3 -PREHOOK: query: explain +PREHOOK: query: explain vectorization detail select insert_num,a,b from table_add_int_permute_select PREHOOK: type: QUERY -POSTHOOK: query: explain +POSTHOOK: query: explain vectorization detail select insert_num,a,b from table_add_int_permute_select POSTHOOK: type: QUERY Explain -Plan optimized by CBO. +PLAN VECTORIZATION: + enabled: false + enabledConditionsNotMet: [hive.vectorized.execution.enabled IS false] -Stage-0 - Fetch Operator - limit:-1 - Stage-1 - Map 1 llap - File Output Operator [FS_2] - Select Operator [SEL_1] (rows=6 width=20) - Output:["_col0","_col1","_col2"] - TableScan [TS_0] (rows=6 width=20) - default@table_add_int_permute_select,table_add_int_permute_select,Tbl:COMPLETE,Col:NONE,Output:["insert_num","a","b"] +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: table_add_int_permute_select + Statistics: Num rows: 6 Data size: 120 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: insert_num (type: int), a (type: int), b (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 6 Data size: 120 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 6 Data size: 120 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 + Execution mode: llap + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink PREHOOK: query: select insert_num,a,b from table_add_int_permute_select PREHOOK: type: QUERY @@ -168,25 +192,49 @@ POSTHOOK: Lineage: table_add_int_string_permute_select.c EXPRESSION [(values__tm POSTHOOK: Lineage: table_add_int_string_permute_select.d SIMPLE [(values__tmp__table__2)values__tmp__table__2.FieldSchema(name:tmp_values_col5, type:string, comment:), ] POSTHOOK: Lineage: table_add_int_string_permute_select.insert_num EXPRESSION [(values__tmp__table__2)values__tmp__table__2.FieldSchema(name:tmp_values_col1, type:string, comment:), ] _col0 _col1 _col2 _col3 _col4 -PREHOOK: query: explain +PREHOOK: query: explain vectorization detail select insert_num,a,b from table_add_int_string_permute_select PREHOOK: type: QUERY -POSTHOOK: query: explain +POSTHOOK: query: explain vectorization detail select insert_num,a,b from table_add_int_string_permute_select POSTHOOK: type: QUERY Explain -Plan optimized by CBO. +PLAN VECTORIZATION: + enabled: false + enabledConditionsNotMet: [hive.vectorized.execution.enabled IS false] + +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 -Stage-0 - Fetch Operator - limit:-1 - Stage-1 - Map 1 llap - File Output Operator [FS_2] - Select Operator [SEL_1] (rows=6 width=21) - Output:["_col0","_col1","_col2"] - TableScan [TS_0] (rows=6 width=21) - default@table_add_int_string_permute_select,table_add_int_string_permute_select,Tbl:COMPLETE,Col:NONE,Output:["insert_num","a","b"] +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: table_add_int_string_permute_select + Statistics: Num rows: 6 Data size: 127 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: insert_num (type: int), a (type: int), b (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 6 Data size: 127 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 6 Data size: 127 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 + Execution mode: llap + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink PREHOOK: query: select insert_num,a,b from table_add_int_string_permute_select PREHOOK: type: QUERY @@ -343,25 +391,49 @@ POSTHOOK: Lineage: table_change_string_group_double.c2 EXPRESSION [(values__tmp_ POSTHOOK: Lineage: table_change_string_group_double.c3 EXPRESSION [(values__tmp__table__3)values__tmp__table__3.FieldSchema(name:tmp_values_col4, type:string, comment:), ] POSTHOOK: Lineage: table_change_string_group_double.insert_num EXPRESSION [(values__tmp__table__3)values__tmp__table__3.FieldSchema(name:tmp_values_col1, type:string, comment:), ] _col0 _col1 _col2 _col3 _col4 -PREHOOK: query: explain +PREHOOK: query: explain vectorization detail select insert_num,c1,c2,c3,b from table_change_string_group_double PREHOOK: type: QUERY -POSTHOOK: query: explain +POSTHOOK: query: explain vectorization detail select insert_num,c1,c2,c3,b from table_change_string_group_double POSTHOOK: type: QUERY Explain -Plan optimized by CBO. +PLAN VECTORIZATION: + enabled: false + enabledConditionsNotMet: [hive.vectorized.execution.enabled IS false] -Stage-0 - Fetch Operator - limit:-1 - Stage-1 - Map 1 llap - File Output Operator [FS_2] - Select Operator [SEL_1] (rows=6 width=80) - Output:["_col0","_col1","_col2","_col3","_col4"] - TableScan [TS_0] (rows=6 width=80) - default@table_change_string_group_double,table_change_string_group_double,Tbl:COMPLETE,Col:NONE,Output:["insert_num","c1","c2","c3","b"] +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: table_change_string_group_double + Statistics: Num rows: 6 Data size: 482 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: insert_num (type: int), c1 (type: double), c2 (type: double), c3 (type: double), b (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4 + Statistics: Num rows: 6 Data size: 482 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 6 Data size: 482 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 + Execution mode: llap + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink PREHOOK: query: select insert_num,c1,c2,c3,b from table_change_string_group_double PREHOOK: type: QUERY @@ -587,25 +659,49 @@ POSTHOOK: Lineage: table_change_numeric_group_string_group_multi_ints_string_gro POSTHOOK: Lineage: table_change_numeric_group_string_group_multi_ints_string_group.c9 EXPRESSION [(values__tmp__table__5)values__tmp__table__5.FieldSchema(name:tmp_values_col10, type:string, comment:), ] POSTHOOK: Lineage: table_change_numeric_group_string_group_multi_ints_string_group.insert_num EXPRESSION [(values__tmp__table__5)values__tmp__table__5.FieldSchema(name:tmp_values_col1, type:string, comment:), ] _col0 _col1 _col2 _col3 _col4 _col5 _col6 _col7 _col8 _col9 _col10 _col11 _col12 _col13 _col14 _col15 _col16 _col17 _col18 _col19 _col20 _col21 -PREHOOK: query: explain +PREHOOK: query: explain vectorization detail select insert_num,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,c16,c17,c18,c19,c20,b from table_change_numeric_group_string_group_multi_ints_string_group PREHOOK: type: QUERY -POSTHOOK: query: explain +POSTHOOK: query: explain vectorization detail select insert_num,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,c16,c17,c18,c19,c20,b from table_change_numeric_group_string_group_multi_ints_string_group POSTHOOK: type: QUERY Explain -Plan optimized by CBO. +PLAN VECTORIZATION: + enabled: false + enabledConditionsNotMet: [hive.vectorized.execution.enabled IS false] + +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: table_change_numeric_group_string_group_multi_ints_string_group + Statistics: Num rows: 6 Data size: 1070 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: insert_num (type: int), c1 (type: string), c2 (type: string), c3 (type: string), c4 (type: string), c5 (type: char(50)), c6 (type: char(50)), c7 (type: char(50)), c8 (type: char(50)), c9 (type: char(5)), c10 (type: char(5)), c11 (type: char(5)), c12 (type: char(5)), c13 (type: varchar(50)), c14 (type: varchar(50)), c15 (type: varchar(50)), c16 (type: varchar(50)), c17 (type: varchar(5)), c18 (type: varchar(5)), c19 (type: varchar(5)), c20 (type: varchar(5)), b (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21 + Statistics: Num rows: 6 Data size: 1070 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 6 Data size: 1070 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 + Execution mode: llap -Stage-0 - Fetch Operator - limit:-1 - Stage-1 - Map 1 llap - File Output Operator [FS_2] - Select Operator [SEL_1] (rows=6 width=178) - Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17","_col18","_col19","_col20","_col21"] - TableScan [TS_0] (rows=6 width=178) - default@table_change_numeric_group_string_group_multi_ints_string_group,table_change_numeric_group_string_group_multi_ints_string_group,Tbl:COMPLETE,Col:NONE,Output:["insert_num","c1","c2","c3","c4","c5","c6","c7","c8","c9","c10","c11","c12","c13","c14","c15","c16","c17","c18","c19","c20","b"] + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink PREHOOK: query: select insert_num,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,c16,c17,c18,c19,c20,b from table_change_numeric_group_string_group_multi_ints_string_group PREHOOK: type: QUERY @@ -742,25 +838,49 @@ POSTHOOK: Lineage: table_change_numeric_group_string_group_floating_string_group POSTHOOK: Lineage: table_change_numeric_group_string_group_floating_string_group.c9 EXPRESSION [(values__tmp__table__6)values__tmp__table__6.FieldSchema(name:tmp_values_col10, type:string, comment:), ] POSTHOOK: Lineage: table_change_numeric_group_string_group_floating_string_group.insert_num EXPRESSION [(values__tmp__table__6)values__tmp__table__6.FieldSchema(name:tmp_values_col1, type:string, comment:), ] _col0 _col1 _col2 _col3 _col4 _col5 _col6 _col7 _col8 _col9 _col10 _col11 _col12 _col13 _col14 _col15 _col16 -PREHOOK: query: explain +PREHOOK: query: explain vectorization detail select insert_num,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,b from table_change_numeric_group_string_group_floating_string_group PREHOOK: type: QUERY -POSTHOOK: query: explain +POSTHOOK: query: explain vectorization detail select insert_num,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,b from table_change_numeric_group_string_group_floating_string_group POSTHOOK: type: QUERY Explain -Plan optimized by CBO. +PLAN VECTORIZATION: + enabled: false + enabledConditionsNotMet: [hive.vectorized.execution.enabled IS false] + +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: table_change_numeric_group_string_group_floating_string_group + Statistics: Num rows: 6 Data size: 1497 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: insert_num (type: int), c1 (type: string), c2 (type: string), c3 (type: string), c4 (type: char(50)), c5 (type: char(50)), c6 (type: char(50)), c7 (type: char(7)), c8 (type: char(7)), c9 (type: char(7)), c10 (type: varchar(50)), c11 (type: varchar(50)), c12 (type: varchar(50)), c13 (type: varchar(7)), c14 (type: varchar(7)), c15 (type: varchar(7)), b (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16 + Statistics: Num rows: 6 Data size: 1497 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 6 Data size: 1497 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 + Execution mode: llap -Stage-0 - Fetch Operator - limit:-1 - Stage-1 - Map 1 llap - File Output Operator [FS_2] - Select Operator [SEL_1] (rows=6 width=249) - Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16"] - TableScan [TS_0] (rows=6 width=249) - default@table_change_numeric_group_string_group_floating_string_group,table_change_numeric_group_string_group_floating_string_group,Tbl:COMPLETE,Col:NONE,Output:["insert_num","c1","c2","c3","c4","c5","c6","c7","c8","c9","c10","c11","c12","c13","c14","c15","b"] + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink PREHOOK: query: select insert_num,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,b from table_change_numeric_group_string_group_floating_string_group PREHOOK: type: QUERY diff --git ql/src/test/results/clientpositive/llap/vector_bucket.q.out ql/src/test/results/clientpositive/llap/vector_bucket.q.out index 7917ffd..18dcce2 100644 --- ql/src/test/results/clientpositive/llap/vector_bucket.q.out +++ ql/src/test/results/clientpositive/llap/vector_bucket.q.out @@ -57,7 +57,7 @@ STAGE PLANS: enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true groupByVectorOutput: true allNative: false - usesVectorUDFAdaptor: true + usesVectorUDFAdaptor: false vectorized: true Reduce Operator Tree: Select Operator @@ -67,7 +67,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [2, 1] - selectExpressions: VectorUDFAdaptor(UDFToInteger(VALUE._col0)) -> 2:int + selectExpressions: CastStringToLong(col 0) -> 2:int Statistics: Num rows: 1 Data size: 26 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false diff --git ql/src/test/results/clientpositive/llap/vector_char_2.q.out ql/src/test/results/clientpositive/llap/vector_char_2.q.out index c2d0c42..98db4c1 100644 --- ql/src/test/results/clientpositive/llap/vector_char_2.q.out +++ ql/src/test/results/clientpositive/llap/vector_char_2.q.out @@ -91,7 +91,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [1, 2] - selectExpressions: VectorUDFAdaptor(UDFToInteger(key)) -> 2:int + selectExpressions: CastStringToLong(col 0) -> 2:int Statistics: Num rows: 500 Data size: 99000 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: sum(_col1), count() @@ -126,7 +126,7 @@ STAGE PLANS: groupByVectorOutput: true inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat allNative: false - usesVectorUDFAdaptor: true + usesVectorUDFAdaptor: false vectorized: true Reducer 2 Execution mode: vectorized, llap @@ -289,7 +289,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [1, 2] - selectExpressions: VectorUDFAdaptor(UDFToInteger(key)) -> 2:int + selectExpressions: CastStringToLong(col 0) -> 2:int Statistics: Num rows: 500 Data size: 99000 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: sum(_col1), count() @@ -324,7 +324,7 @@ STAGE PLANS: groupByVectorOutput: true inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat allNative: false - usesVectorUDFAdaptor: true + usesVectorUDFAdaptor: false vectorized: true Reducer 2 Execution mode: vectorized, llap diff --git ql/src/test/results/clientpositive/llap/vector_coalesce_2.q.out ql/src/test/results/clientpositive/llap/vector_coalesce_2.q.out index ae6aecc..5a283bc 100644 --- ql/src/test/results/clientpositive/llap/vector_coalesce_2.q.out +++ ql/src/test/results/clientpositive/llap/vector_coalesce_2.q.out @@ -219,7 +219,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [1, 4] - selectExpressions: VectorUDFAdaptor(UDFToInteger(COALESCE(str1,0)))(children: VectorCoalesce(columns [0, 2])(children: col 0, ConstantVectorExpression(val 0) -> 2:string) -> 3:string) -> 4:int + selectExpressions: CastStringToLong(col 3)(children: VectorCoalesce(columns [0, 2])(children: col 0, ConstantVectorExpression(val 0) -> 2:string) -> 3:string) -> 4:int Statistics: Num rows: 4 Data size: 510 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: sum(_col1) @@ -252,7 +252,7 @@ STAGE PLANS: groupByVectorOutput: true inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat allNative: false - usesVectorUDFAdaptor: true + usesVectorUDFAdaptor: false vectorized: true Reducer 2 Execution mode: vectorized, llap diff --git ql/src/test/results/clientpositive/llap/vector_empty_where.q.out ql/src/test/results/clientpositive/llap/vector_empty_where.q.out index 9f93f86..ed9d551 100644 --- ql/src/test/results/clientpositive/llap/vector_empty_where.q.out +++ ql/src/test/results/clientpositive/llap/vector_empty_where.q.out @@ -62,7 +62,7 @@ STAGE PLANS: Reduce Sink Vectorization: className: VectorReduceSinkLongOperator native: true - nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, Not ACID UPDATE or DELETE IS true, No buckets IS true, No TopN IS true, Uniform Hash IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true + nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No buckets IS true, No TopN IS true, Uniform Hash IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true Statistics: Num rows: 2888 Data size: 8628 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: all inputs @@ -111,7 +111,7 @@ STAGE PLANS: Reduce Sink Vectorization: className: VectorReduceSinkOperator native: false - nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, Not ACID UPDATE or DELETE IS true, No buckets IS true, No TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true + nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No buckets IS true, No TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: Uniform Hash IS false Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) @@ -218,7 +218,7 @@ STAGE PLANS: Reduce Sink Vectorization: className: VectorReduceSinkLongOperator native: true - nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, Not ACID UPDATE or DELETE IS true, No buckets IS true, No TopN IS true, Uniform Hash IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true + nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No buckets IS true, No TopN IS true, Uniform Hash IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true Statistics: Num rows: 2888 Data size: 8628 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: all inputs @@ -267,7 +267,7 @@ STAGE PLANS: Reduce Sink Vectorization: className: VectorReduceSinkOperator native: false - nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, Not ACID UPDATE or DELETE IS true, No buckets IS true, No TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true + nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No buckets IS true, No TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: Uniform Hash IS false Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) @@ -382,7 +382,7 @@ STAGE PLANS: Reduce Sink Vectorization: className: VectorReduceSinkLongOperator native: true - nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, Not ACID UPDATE or DELETE IS true, No buckets IS true, No TopN IS true, Uniform Hash IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true + nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No buckets IS true, No TopN IS true, Uniform Hash IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true Statistics: Num rows: 2888 Data size: 8628 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: all inputs @@ -431,7 +431,7 @@ STAGE PLANS: Reduce Sink Vectorization: className: VectorReduceSinkOperator native: false - nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, Not ACID UPDATE or DELETE IS true, No buckets IS true, No TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true + nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No buckets IS true, No TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: Uniform Hash IS false Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) @@ -546,7 +546,7 @@ STAGE PLANS: Reduce Sink Vectorization: className: VectorReduceSinkLongOperator native: true - nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, Not ACID UPDATE or DELETE IS true, No buckets IS true, No TopN IS true, Uniform Hash IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true + nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No buckets IS true, No TopN IS true, Uniform Hash IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true Statistics: Num rows: 2888 Data size: 8628 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: all inputs @@ -595,7 +595,7 @@ STAGE PLANS: Reduce Sink Vectorization: className: VectorReduceSinkOperator native: false - nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, Not ACID UPDATE or DELETE IS true, No buckets IS true, No TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true + nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No buckets IS true, No TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: Uniform Hash IS false Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) diff --git ql/src/test/results/clientpositive/llap/vector_non_string_partition.q.out ql/src/test/results/clientpositive/llap/vector_non_string_partition.q.out index ae52b60..81dafa1 100644 --- ql/src/test/results/clientpositive/llap/vector_non_string_partition.q.out +++ ql/src/test/results/clientpositive/llap/vector_non_string_partition.q.out @@ -27,10 +27,14 @@ POSTHOOK: query: SHOW PARTITIONS non_string_part POSTHOOK: type: SHOWPARTITIONS POSTHOOK: Input: default@non_string_part ctinyint=__HIVE_DEFAULT_PARTITION__ -PREHOOK: query: EXPLAIN SELECT cint, ctinyint FROM non_string_part WHERE cint > 0 ORDER BY cint LIMIT 10 +PREHOOK: query: EXPLAIN VECTORIZATION EXPRESSION SELECT cint, ctinyint FROM non_string_part WHERE cint > 0 ORDER BY cint LIMIT 10 PREHOOK: type: QUERY -POSTHOOK: query: EXPLAIN SELECT cint, ctinyint FROM non_string_part WHERE cint > 0 ORDER BY cint LIMIT 10 +POSTHOOK: query: EXPLAIN VECTORIZATION EXPRESSION SELECT cint, ctinyint FROM non_string_part WHERE cint > 0 ORDER BY cint LIMIT 10 POSTHOOK: type: QUERY +PLAN VECTORIZATION: + enabled: true + enabledConditionsMet: [hive.vectorized.execution.enabled IS true] + STAGE DEPENDENCIES: Stage-1 is a root stage Stage-0 depends on stages: Stage-1 @@ -38,6 +42,7 @@ STAGE DEPENDENCIES: STAGE PLANS: Stage: Stage-1 Tez +#### A masked pattern was here #### Edges: Reducer 2 <- Map 1 (SIMPLE_EDGE) #### A masked pattern was here #### @@ -46,36 +51,79 @@ STAGE PLANS: Map Operator Tree: TableScan alias: non_string_part - Statistics: Num rows: 3073 Data size: 339150 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3073 Data size: 351442 Basic stats: COMPLETE Column stats: PARTIAL + TableScan Vectorization: + native: true + projectedOutputColumns: [0, 1, 2, 3, 4] Filter Operator + Filter Vectorization: + className: VectorFilterOperator + native: true + predicateExpression: FilterLongColGreaterLongScalar(col 0, val 0) -> boolean predicate: (cint > 0) (type: boolean) - Statistics: Num rows: 1024 Data size: 113013 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1024 Data size: 4096 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: cint (type: int), ctinyint (type: tinyint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1024 Data size: 113013 Basic stats: COMPLETE Column stats: NONE + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumns: [0, 4] + Statistics: Num rows: 1024 Data size: 4096 Basic stats: COMPLETE Column stats: PARTIAL Reduce Output Operator key expressions: _col0 (type: int) sort order: + - Statistics: Num rows: 1024 Data size: 113013 Basic stats: COMPLETE Column stats: NONE + Reduce Sink Vectorization: + className: VectorReduceSinkOperator + native: false + nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No buckets IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true + nativeConditionsNotMet: No TopN IS false, Uniform Hash IS false + Statistics: Num rows: 1024 Data size: 4096 Basic stats: COMPLETE Column stats: PARTIAL + TopN Hash Memory Usage: 0.1 value expressions: _col1 (type: tinyint) Execution mode: vectorized, llap + LLAP IO: all inputs + Map Vectorization: + enabled: true + enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true + groupByVectorOutput: true + inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + allNative: false + usesVectorUDFAdaptor: false + vectorized: true Reducer 2 - Execution mode: vectorized, uber + Execution mode: vectorized, llap + Reduce Vectorization: + enabled: true + enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true + groupByVectorOutput: true + allNative: false + usesVectorUDFAdaptor: false + vectorized: true Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: tinyint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1024 Data size: 113013 Basic stats: COMPLETE Column stats: NONE + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumns: [0, 1] + Statistics: Num rows: 1024 Data size: 4096 Basic stats: COMPLETE Column stats: PARTIAL Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 1100 Basic stats: COMPLETE Column stats: NONE + Limit Vectorization: + className: VectorLimitOperator + native: true + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 1100 Basic stats: COMPLETE Column stats: NONE + File Sink Vectorization: + className: VectorFileSinkOperator + native: false + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: PARTIAL table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 @@ -104,10 +152,14 @@ POSTHOOK: Input: default@non_string_part@ctinyint=__HIVE_DEFAULT_PARTITION__ 799471 NULL 1248059 NULL 1286921 NULL -PREHOOK: query: EXPLAIN SELECT cint, cstring1 FROM non_string_part WHERE cint > 0 ORDER BY cint, cstring1 LIMIT 10 +PREHOOK: query: EXPLAIN VECTORIZATION EXPRESSION SELECT cint, cstring1 FROM non_string_part WHERE cint > 0 ORDER BY cint, cstring1 LIMIT 10 PREHOOK: type: QUERY -POSTHOOK: query: EXPLAIN SELECT cint, cstring1 FROM non_string_part WHERE cint > 0 ORDER BY cint, cstring1 LIMIT 10 +POSTHOOK: query: EXPLAIN VECTORIZATION EXPRESSION SELECT cint, cstring1 FROM non_string_part WHERE cint > 0 ORDER BY cint, cstring1 LIMIT 10 POSTHOOK: type: QUERY +PLAN VECTORIZATION: + enabled: true + enabledConditionsMet: [hive.vectorized.execution.enabled IS true] + STAGE DEPENDENCIES: Stage-1 is a root stage Stage-0 depends on stages: Stage-1 @@ -115,6 +167,7 @@ STAGE DEPENDENCIES: STAGE PLANS: Stage: Stage-1 Tez +#### A masked pattern was here #### Edges: Reducer 2 <- Map 1 (SIMPLE_EDGE) #### A masked pattern was here #### @@ -123,35 +176,78 @@ STAGE PLANS: Map Operator Tree: TableScan alias: non_string_part - Statistics: Num rows: 3073 Data size: 339150 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3073 Data size: 363734 Basic stats: COMPLETE Column stats: NONE + TableScan Vectorization: + native: true + projectedOutputColumns: [0, 1, 2, 3, 4] Filter Operator + Filter Vectorization: + className: VectorFilterOperator + native: true + predicateExpression: FilterLongColGreaterLongScalar(col 0, val 0) -> boolean predicate: (cint > 0) (type: boolean) - Statistics: Num rows: 1024 Data size: 113013 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1024 Data size: 121205 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cint (type: int), cstring1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1024 Data size: 113013 Basic stats: COMPLETE Column stats: NONE + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumns: [0, 1] + Statistics: Num rows: 1024 Data size: 121205 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: string) sort order: ++ - Statistics: Num rows: 1024 Data size: 113013 Basic stats: COMPLETE Column stats: NONE + Reduce Sink Vectorization: + className: VectorReduceSinkOperator + native: false + nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No buckets IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true + nativeConditionsNotMet: No TopN IS false, Uniform Hash IS false + Statistics: Num rows: 1024 Data size: 121205 Basic stats: COMPLETE Column stats: NONE + TopN Hash Memory Usage: 0.1 Execution mode: vectorized, llap + LLAP IO: all inputs + Map Vectorization: + enabled: true + enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true + groupByVectorOutput: true + inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + allNative: false + usesVectorUDFAdaptor: false + vectorized: true Reducer 2 - Execution mode: vectorized, uber + Execution mode: vectorized, llap + Reduce Vectorization: + enabled: true + enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true + groupByVectorOutput: true + allNative: false + usesVectorUDFAdaptor: false + vectorized: true Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1024 Data size: 113013 Basic stats: COMPLETE Column stats: NONE + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumns: [0, 1] + Statistics: Num rows: 1024 Data size: 121205 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 1100 Basic stats: COMPLETE Column stats: NONE + Limit Vectorization: + className: VectorLimitOperator + native: true + Statistics: Num rows: 10 Data size: 1180 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 1100 Basic stats: COMPLETE Column stats: NONE + File Sink Vectorization: + className: VectorFileSinkOperator + native: false + Statistics: Num rows: 10 Data size: 1180 Basic stats: COMPLETE Column stats: NONE table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 diff --git ql/src/test/results/clientpositive/llap/vector_tablesample_rows.q.out ql/src/test/results/clientpositive/llap/vector_tablesample_rows.q.out index 56fb85c..aa63cb1 100644 --- ql/src/test/results/clientpositive/llap/vector_tablesample_rows.q.out +++ ql/src/test/results/clientpositive/llap/vector_tablesample_rows.q.out @@ -264,7 +264,7 @@ STAGE PLANS: Reduce Sink Vectorization: className: VectorReduceSinkOperator native: false - nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, Not ACID UPDATE or DELETE IS true, No buckets IS true, No TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true + nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No buckets IS true, No TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: Uniform Hash IS false Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) diff --git ql/src/test/results/clientpositive/llap/vectorization_div0.q.out ql/src/test/results/clientpositive/llap/vectorization_div0.q.out index 2b61979..37d05c8 100644 --- ql/src/test/results/clientpositive/llap/vectorization_div0.q.out +++ ql/src/test/results/clientpositive/llap/vectorization_div0.q.out @@ -1,27 +1,71 @@ -PREHOOK: query: -- TODO: add more stuff here after HIVE-5918 is fixed, such as cbigint and constants -explain +PREHOOK: query: explain vectorization expression select cdouble / 0.0 from alltypesorc limit 100 PREHOOK: type: QUERY -POSTHOOK: query: -- TODO: add more stuff here after HIVE-5918 is fixed, such as cbigint and constants -explain +POSTHOOK: query: explain vectorization expression select cdouble / 0.0 from alltypesorc limit 100 POSTHOOK: type: QUERY +PLAN VECTORIZATION: + enabled: true + enabledConditionsMet: [hive.vectorized.execution.enabled IS true] + STAGE DEPENDENCIES: - Stage-0 is a root stage + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: alltypesorc + Statistics: Num rows: 12288 Data size: 73400 Basic stats: COMPLETE Column stats: COMPLETE + TableScan Vectorization: + native: true + projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11] + Select Operator + expressions: (cdouble / 0.0) (type: double) + outputColumnNames: _col0 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumns: [12] + selectExpressions: DoubleColDivideDoubleScalar(col 5, val 0.0) -> 12:double + Statistics: Num rows: 12288 Data size: 98304 Basic stats: COMPLETE Column stats: COMPLETE + Limit + Number of rows: 100 + Limit Vectorization: + className: VectorLimitOperator + native: true + Statistics: Num rows: 100 Data size: 800 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + File Sink Vectorization: + className: VectorFileSinkOperator + native: false + Statistics: Num rows: 100 Data size: 800 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 + Execution mode: vectorized, llap + LLAP IO: all inputs + Map Vectorization: + enabled: true + enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true + groupByVectorOutput: true + inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + allNative: false + usesVectorUDFAdaptor: false + vectorized: true + Stage: Stage-0 Fetch Operator limit: 100 Processor Tree: - TableScan - alias: alltypesorc - Select Operator - expressions: (cdouble / 0.0) (type: double) - outputColumnNames: _col0 - Limit - Number of rows: 100 - ListSink + ListSink PREHOOK: query: select cdouble / 0.0 from alltypesorc limit 100 PREHOOK: type: QUERY @@ -131,20 +175,18 @@ NULL NULL NULL NULL -PREHOOK: query: -- There are no zeros in the table, but there is 988888, so use it as zero - --- TODO: add more stuff here after HIVE-5918 is fixed, such as cbigint and constants as numerators -explain +PREHOOK: query: explain vectorization expression select (cbigint - 988888L) as s1, cdouble / (cbigint - 988888L) as s2, 1.2 / (cbigint - 988888L) from alltypesorc where cbigint > 0 and cbigint < 100000000 order by s1, s2 limit 100 PREHOOK: type: QUERY -POSTHOOK: query: -- There are no zeros in the table, but there is 988888, so use it as zero - --- TODO: add more stuff here after HIVE-5918 is fixed, such as cbigint and constants as numerators -explain +POSTHOOK: query: explain vectorization expression select (cbigint - 988888L) as s1, cdouble / (cbigint - 988888L) as s2, 1.2 / (cbigint - 988888L) from alltypesorc where cbigint > 0 and cbigint < 100000000 order by s1, s2 limit 100 POSTHOOK: type: QUERY +PLAN VECTORIZATION: + enabled: true + enabledConditionsMet: [hive.vectorized.execution.enabled IS true] + STAGE DEPENDENCIES: Stage-1 is a root stage Stage-0 depends on stages: Stage-1 @@ -152,6 +194,7 @@ STAGE DEPENDENCIES: STAGE PLANS: Stage: Stage-1 Tez +#### A masked pattern was here #### Edges: Reducer 2 <- Map 1 (SIMPLE_EDGE) #### A masked pattern was here #### @@ -160,36 +203,80 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 146792 Basic stats: COMPLETE Column stats: COMPLETE + TableScan Vectorization: + native: true + projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11] Filter Operator + Filter Vectorization: + className: VectorFilterOperator + native: true + predicateExpression: FilterExprAndExpr(children: FilterLongColGreaterLongScalar(col 3, val 0) -> boolean, FilterLongColLessLongScalar(col 3, val 100000000) -> boolean) -> boolean predicate: ((cbigint > 0) and (cbigint < 100000000)) (type: boolean) - Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1365 Data size: 16320 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: (cbigint - 988888) (type: bigint), (cdouble / UDFToDouble((cbigint - 988888))) (type: double), (1.2 / UDFToDouble((cbigint - 988888))) (type: double) + expressions: (cbigint - 988888) (type: bigint), (cdouble / UDFToDouble((cbigint - 988888))) (type: double), (1.2 / CAST( (cbigint - 988888) AS decimal(19,0))) (type: decimal(22,21)) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumns: [12, 15, 17] + selectExpressions: LongColSubtractLongScalar(col 3, val 988888) -> 12:long, DoubleColDivideDoubleColumn(col 5, col 14)(children: CastLongToDouble(col 13)(children: LongColSubtractLongScalar(col 3, val 988888) -> 13:long) -> 14:double) -> 15:double, DecimalScalarDivideDecimalColumn(val 1.2, col 16)(children: CastLongToDecimal(col 13)(children: LongColSubtractLongScalar(col 3, val 988888) -> 13:long) -> 16:decimal(19,0)) -> 17:decimal(22,21) + Statistics: Num rows: 1365 Data size: 174720 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: bigint), _col1 (type: double) sort order: ++ - Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: double) + Reduce Sink Vectorization: + className: VectorReduceSinkOperator + native: false + nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No buckets IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true + nativeConditionsNotMet: No TopN IS false, Uniform Hash IS false + Statistics: Num rows: 1365 Data size: 174720 Basic stats: COMPLETE Column stats: COMPLETE + TopN Hash Memory Usage: 0.1 + value expressions: _col2 (type: decimal(22,21)) Execution mode: vectorized, llap + LLAP IO: all inputs + Map Vectorization: + enabled: true + enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true + groupByVectorOutput: true + inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + allNative: false + usesVectorUDFAdaptor: false + vectorized: true Reducer 2 - Execution mode: vectorized, uber + Execution mode: vectorized, llap + Reduce Vectorization: + enabled: true + enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true + groupByVectorOutput: true + allNative: false + usesVectorUDFAdaptor: false + vectorized: true Reduce Operator Tree: Select Operator - expressions: KEY.reducesinkkey0 (type: bigint), KEY.reducesinkkey1 (type: double), VALUE._col0 (type: double) + expressions: KEY.reducesinkkey0 (type: bigint), KEY.reducesinkkey1 (type: double), VALUE._col0 (type: decimal(22,21)) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumns: [0, 1, 2] + Statistics: Num rows: 1365 Data size: 174720 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 100 - Statistics: Num rows: 100 Data size: 21500 Basic stats: COMPLETE Column stats: NONE + Limit Vectorization: + className: VectorLimitOperator + native: true + Statistics: Num rows: 100 Data size: 12800 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 100 Data size: 21500 Basic stats: COMPLETE Column stats: NONE + File Sink Vectorization: + className: VectorFileSinkOperator + native: false + Statistics: Num rows: 100 Data size: 12800 Basic stats: COMPLETE Column stats: COMPLETE table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 @@ -208,9 +295,9 @@ from alltypesorc where cbigint > 0 and cbigint < 100000000 order by s1, s2 limit POSTHOOK: type: QUERY POSTHOOK: Input: default@alltypesorc #### A masked pattern was here #### --985319 NULL -1.21787969175465E-6 --985319 2.0297994862577501E-4 -1.21787969175465E-6 --63925 0.11256941728588189 -1.8771998435666796E-5 +-985319 NULL -0.000001217879691754650 +-985319 2.0297994862577501E-4 -0.000001217879691754650 +-63925 0.11256941728588189 -0.000018771998435666797 0 NULL NULL 0 NULL NULL 0 NULL NULL @@ -220,106 +307,106 @@ POSTHOOK: Input: default@alltypesorc 0 NULL NULL 0 NULL NULL 0 NULL NULL -392309 NULL 3.05881333336732E-6 -673083 -0.010691103474608629 1.7828410463494101E-6 -2331159 NULL 5.147654021025593E-7 -2342037 NULL 5.123744842630582E-7 -3533105 -5.660743170667161E-5 3.3964459024002967E-7 -3768727 0.004139594085748318 3.184099033970887E-7 -4728619 NULL 2.5377388197272816E-7 -5391403 NULL 2.2257657236901044E-7 -7022666 -0.0010246820794268159 1.708752772807364E-7 -7470430 NULL 1.6063332365071354E-7 -8276429 NULL 1.4499006757624573E-7 -8286860 -8.683626850218298E-4 1.44807562816314E-7 -8299981 -8.669899364829872E-4 1.445786442161735E-7 -9247593 NULL 1.297634962957388E-7 -9821695 -7.326637611939691E-4 1.2217850381222386E-7 -10000738 0.001559984873116364 1.1999114465352456E-7 -10081828 0.0015474376273826532 1.190260337708598E-7 -10745355 -6.696847149303117E-4 1.1167616146697805E-7 -11127199 -1.797397530142132E-5 1.0784385180852791E-7 -11722580 NULL 1.023665438836843E-7 -12649396 NULL 9.486618965838368E-8 -13126214 -1.5236685917203544E-5 9.142011550322126E-8 -14042667 NULL 8.545385288991044E-8 -14943972 -1.3383322720358416E-5 8.02999363221505E-8 -16259022 NULL 7.380517721176587E-8 -16531556 -1.2098074736582569E-5 7.258844841949542E-8 -16596157 NULL 7.230589587697923E-8 -17058489 -1.1724367849930905E-5 7.034620709958544E-8 -17247320 -4.172242412154468E-4 6.957602688417679E-8 -19004427 8.209139901981786E-4 6.314318237534864E-8 -19498517 NULL 6.154314197331007E-8 -20165679 7.736411950224934E-4 5.95070466013071E-8 -20547875 NULL 5.840019953401507E-8 -23264783 NULL 5.158010715165492E-8 -23475527 6.645644206411213E-4 5.111706331448917E-8 -24379905 NULL 4.922086447834805E-8 -24514624 -2.935390728407664E-4 4.895037345871591E-8 -25154198 -2.860755091456305E-4 4.770575472133916E-8 -25245192 -7.922300610745999E-6 4.7533803664475993E-8 -26610943 NULL 4.509423059528556E-8 -27520143 5.668938566198584E-4 4.360442458456702E-8 -27818379 NULL 4.313694913711543E-8 -28400244 NULL 4.225315810666979E-8 -28698999 5.43607810153936E-4 4.18133050563889E-8 -28806400 -6.9429015774272385E-6 4.165740946456343E-8 -29920877 5.214085135271938E-4 4.010577631130264E-8 -33126539 NULL 3.622473207961749E-8 -34603086 NULL 3.467898787986713E-8 -35156265 NULL 3.413331876978399E-8 -35862260 NULL 3.346136021544654E-8 -36123797 -1.992038655294182E-4 3.321909931007529E-8 -36341671 -1.980096072082101E-4 3.301994561559924E-8 -36413215 -5.4925114412446145E-6 3.2955068647467685E-8 -36578596 4.2650625518814335E-4 3.280607052277239E-8 -36796441 -1.955623914823719E-4 3.2611849607955287E-8 -39723587 NULL 3.0208752296211316E-8 -39985709 -1.7996429674411925E-4 3.001072208073139E-8 -40018606 NULL 2.998605198791782E-8 -41003161 NULL 2.9266036342905367E-8 -41158231 3.790493328053871E-4 2.9155772025284565E-8 -41848817 NULL 2.8674645689506587E-8 -44047567 -1.633688416888043E-4 2.724327543448654E-8 -45125678 NULL 2.6592398234991615E-8 -45180154 NULL 2.6560334433565674E-8 -45717793 3.4124569399052136E-4 2.6247986205283355E-8 -46163162 NULL 2.5994753132378583E-8 -46525838 3.353190543284787E-4 2.5792120068852925E-8 -48626663 NULL 2.4677819244968545E-8 -49102701 -1.465499830650864E-4 2.4438574163160596E-8 -50300445 -1.4306036457530346E-4 2.3856647789100076E-8 -50929325 -1.412938420055636E-4 2.356206370298448E-8 -52422534 -1.3726921327381848E-4 2.2890919389741823E-8 -52667422 2.9621727070673783E-4 2.2784483356713376E-8 -52962061 2.945693522010029E-4 2.265772852004381E-8 -53695172 NULL 2.234837798824818E-8 -54760317 NULL 2.1913678841559662E-8 -55020655 2.835480602693661E-4 2.180999117513232E-8 -56102034 NULL 2.1389598815615135E-8 -56131313 NULL 2.13784416551952E-8 -56838351 -3.5187509222426247E-6 2.1112505533455745E-8 -56997841 -3.5089048372902406E-6 2.105342902374144E-8 -57778807 -1.2454393528755274E-4 2.076886080392764E-8 -58080381 NULL 2.0661021490199935E-8 -58307527 NULL 2.058053328174937E-8 -58536385 -1.2293208745295768E-4 2.0500070170031853E-8 -59347745 NULL 2.0219807846111087E-8 -60229567 NULL 1.992376933408802E-8 -60330397 NULL 1.9890470801974003E-8 -PREHOOK: query: -- There are no zeros in the table, but there is -200.0, so use it as zero - -explain +392309 NULL 0.000003058813333367320 +673083 -0.010691103474608629 0.000001782841046349410 +2331159 NULL 0.000000514765402102559 +2342037 NULL 0.000000512374484263058 +3533105 -5.660743170667161E-5 0.000000339644590240030 +3768727 0.004139594085748318 0.000000318409903397089 +4728619 NULL 0.000000253773881972728 +5391403 NULL 0.000000222576572369010 +7022666 -0.0010246820794268159 0.000000170875277280736 +7470430 NULL 0.000000160633323650714 +8276429 NULL 0.000000144990067576246 +8286860 -8.683626850218298E-4 0.000000144807562816314 +8299981 -8.669899364829872E-4 0.000000144578644216174 +9247593 NULL 0.000000129763496295739 +9821695 -7.326637611939691E-4 0.000000122178503812224 +10000738 0.001559984873116364 0.000000119991144653525 +10081828 0.0015474376273826532 0.000000119026033770860 +10745355 -6.696847149303117E-4 0.000000111676161466978 +11127199 -1.797397530142132E-5 0.000000107843851808528 +11722580 NULL 0.000000102366543883684 +12649396 NULL 0.000000094866189658384 +13126214 -1.5236685917203544E-5 0.000000091420115503221 +14042667 NULL 0.000000085453852889910 +14943972 -1.3383322720358416E-5 0.000000080299936322150 +16259022 NULL 0.000000073805177211766 +16531556 -1.2098074736582569E-5 0.000000072588448419495 +16596157 NULL 0.000000072305895876979 +17058489 -1.1724367849930905E-5 0.000000070346207099585 +17247320 -4.172242412154468E-4 0.000000069576026884177 +19004427 8.209139901981786E-4 0.000000063143182375349 +19498517 NULL 0.000000061543141973310 +20165679 7.736411950224934E-4 0.000000059507046601307 +20547875 NULL 0.000000058400199534015 +23264783 NULL 0.000000051580107151655 +23475527 6.645644206411213E-4 0.000000051117063314489 +24379905 NULL 0.000000049220864478348 +24514624 -2.935390728407664E-4 0.000000048950373458716 +25154198 -2.860755091456305E-4 0.000000047705754721339 +25245192 -7.922300610745999E-6 0.000000047533803664476 +26610943 NULL 0.000000045094230595286 +27520143 5.668938566198584E-4 0.000000043604424584567 +27818379 NULL 0.000000043136949137115 +28400244 NULL 0.000000042253158106670 +28698999 5.43607810153936E-4 0.000000041813305056389 +28806400 -6.9429015774272385E-6 0.000000041657409464563 +29920877 5.214085135271938E-4 0.000000040105776311303 +33126539 NULL 0.000000036224732079617 +34603086 NULL 0.000000034678987879867 +35156265 NULL 0.000000034133318769784 +35862260 NULL 0.000000033461360215447 +36123797 -1.992038655294182E-4 0.000000033219099310075 +36341671 -1.980096072082101E-4 0.000000033019945615599 +36413215 -5.4925114412446145E-6 0.000000032955068647468 +36578596 4.2650625518814335E-4 0.000000032806070522772 +36796441 -1.955623914823719E-4 0.000000032611849607955 +39723587 NULL 0.000000030208752296211 +39985709 -1.7996429674411925E-4 0.000000030010722080731 +40018606 NULL 0.000000029986051987918 +41003161 NULL 0.000000029266036342905 +41158231 3.790493328053871E-4 0.000000029155772025285 +41848817 NULL 0.000000028674645689507 +44047567 -1.633688416888043E-4 0.000000027243275434487 +45125678 NULL 0.000000026592398234992 +45180154 NULL 0.000000026560334433566 +45717793 3.4124569399052136E-4 0.000000026247986205283 +46163162 NULL 0.000000025994753132379 +46525838 3.353190543284787E-4 0.000000025792120068853 +48626663 NULL 0.000000024677819244969 +49102701 -1.465499830650864E-4 0.000000024438574163161 +50300445 -1.4306036457530346E-4 0.000000023856647789100 +50929325 -1.412938420055636E-4 0.000000023562063702984 +52422534 -1.3726921327381848E-4 0.000000022890919389742 +52667422 2.9621727070673783E-4 0.000000022784483356713 +52962061 2.945693522010029E-4 0.000000022657728520044 +53695172 NULL 0.000000022348377988248 +54760317 NULL 0.000000021913678841560 +55020655 2.835480602693661E-4 0.000000021809991175132 +56102034 NULL 0.000000021389598815615 +56131313 NULL 0.000000021378441655195 +56838351 -3.5187509222426247E-6 0.000000021112505533456 +56997841 -3.5089048372902406E-6 0.000000021053429023741 +57778807 -1.2454393528755274E-4 0.000000020768860803928 +58080381 NULL 0.000000020661021490200 +58307527 NULL 0.000000020580533281749 +58536385 -1.2293208745295768E-4 0.000000020500070170032 +59347745 NULL 0.000000020219807846111 +60229567 NULL 0.000000019923769334088 +60330397 NULL 0.000000019890470801974 +PREHOOK: query: explain vectorization expression select (cdouble + 200.0) as s1, cbigint / (cdouble + 200.0) as s2, (cdouble + 200.0) / (cdouble + 200.0), cbigint / (cdouble + 200.0), 3 / (cdouble + 200.0), 1.2 / (cdouble + 200.0) from alltypesorc where cdouble >= -500 and cdouble < -199 order by s1, s2 limit 100 PREHOOK: type: QUERY -POSTHOOK: query: -- There are no zeros in the table, but there is -200.0, so use it as zero - -explain +POSTHOOK: query: explain vectorization expression select (cdouble + 200.0) as s1, cbigint / (cdouble + 200.0) as s2, (cdouble + 200.0) / (cdouble + 200.0), cbigint / (cdouble + 200.0), 3 / (cdouble + 200.0), 1.2 / (cdouble + 200.0) from alltypesorc where cdouble >= -500 and cdouble < -199 order by s1, s2 limit 100 POSTHOOK: type: QUERY +PLAN VECTORIZATION: + enabled: true + enabledConditionsMet: [hive.vectorized.execution.enabled IS true] + STAGE DEPENDENCIES: Stage-1 is a root stage Stage-0 depends on stages: Stage-1 @@ -327,6 +414,7 @@ STAGE DEPENDENCIES: STAGE PLANS: Stage: Stage-1 Tez +#### A masked pattern was here #### Edges: Reducer 2 <- Map 1 (SIMPLE_EDGE) #### A masked pattern was here #### @@ -335,36 +423,80 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 146792 Basic stats: COMPLETE Column stats: COMPLETE + TableScan Vectorization: + native: true + projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11] Filter Operator + Filter Vectorization: + className: VectorFilterOperator + native: true + predicateExpression: FilterExprAndExpr(children: FilterDoubleColGreaterEqualDoubleScalar(col 5, val -500.0) -> boolean, FilterDoubleColLessDoubleScalar(col 5, val -199.0) -> boolean) -> boolean predicate: ((cdouble >= -500.0) and (cdouble < -199.0)) (type: boolean) - Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1365 Data size: 16320 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: (cdouble + 200.0) (type: double), (UDFToDouble(cbigint) / (cdouble + 200.0)) (type: double), ((cdouble + 200.0) / (cdouble + 200.0)) (type: double), (3.0 / (cdouble + 200.0)) (type: double), (1.2 / (cdouble + 200.0)) (type: double) outputColumnNames: _col0, _col1, _col2, _col4, _col5 - Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumns: [12, 15, 16, 14, 17] + selectExpressions: DoubleColAddDoubleScalar(col 5, val 200.0) -> 12:double, DoubleColDivideDoubleColumn(col 13, col 14)(children: CastLongToDouble(col 3) -> 13:double, DoubleColAddDoubleScalar(col 5, val 200.0) -> 14:double) -> 15:double, DoubleColDivideDoubleColumn(col 13, col 14)(children: DoubleColAddDoubleScalar(col 5, val 200.0) -> 13:double, DoubleColAddDoubleScalar(col 5, val 200.0) -> 14:double) -> 16:double, DoubleScalarDivideDoubleColumn(val 3.0, col 13)(children: DoubleColAddDoubleScalar(col 5, val 200.0) -> 13:double) -> 14:double, DoubleScalarDivideDoubleColumn(val 1.2, col 13)(children: DoubleColAddDoubleScalar(col 5, val 200.0) -> 13:double) -> 17:double + Statistics: Num rows: 1365 Data size: 65520 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: double), _col1 (type: double) sort order: ++ - Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE + Reduce Sink Vectorization: + className: VectorReduceSinkOperator + native: false + nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No buckets IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true + nativeConditionsNotMet: No TopN IS false, Uniform Hash IS false + Statistics: Num rows: 1365 Data size: 65520 Basic stats: COMPLETE Column stats: COMPLETE + TopN Hash Memory Usage: 0.1 value expressions: _col2 (type: double), _col4 (type: double), _col5 (type: double) Execution mode: vectorized, llap + LLAP IO: all inputs + Map Vectorization: + enabled: true + enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true + groupByVectorOutput: true + inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + allNative: false + usesVectorUDFAdaptor: false + vectorized: true Reducer 2 - Execution mode: vectorized, uber + Execution mode: vectorized, llap + Reduce Vectorization: + enabled: true + enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true + groupByVectorOutput: true + allNative: false + usesVectorUDFAdaptor: false + vectorized: true Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: double), KEY.reducesinkkey1 (type: double), VALUE._col0 (type: double), KEY.reducesinkkey1 (type: double), VALUE._col1 (type: double), VALUE._col2 (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumns: [0, 1, 2, 1, 3, 4] + Statistics: Num rows: 1365 Data size: 65520 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 100 - Statistics: Num rows: 100 Data size: 21500 Basic stats: COMPLETE Column stats: NONE + Limit Vectorization: + className: VectorLimitOperator + native: true + Statistics: Num rows: 100 Data size: 4800 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 100 Data size: 21500 Basic stats: COMPLETE Column stats: NONE + File Sink Vectorization: + className: VectorFileSinkOperator + native: false + Statistics: Num rows: 100 Data size: 4800 Basic stats: COMPLETE Column stats: COMPLETE table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 diff --git ql/src/test/results/clientpositive/llap/vectorization_limit.q.out ql/src/test/results/clientpositive/llap/vectorization_limit.q.out index afaf2d6..5700005 100644 --- ql/src/test/results/clientpositive/llap/vectorization_limit.q.out +++ ql/src/test/results/clientpositive/llap/vectorization_limit.q.out @@ -1,26 +1,59 @@ WARNING: Comparing a bigint and a double may result in a loss of precision. -PREHOOK: query: explain SELECT cbigint, cdouble FROM alltypesorc WHERE cbigint < cdouble and cint > 0 limit 7 +PREHOOK: query: explain vectorization SELECT cbigint, cdouble FROM alltypesorc WHERE cbigint < cdouble and cint > 0 limit 7 PREHOOK: type: QUERY -POSTHOOK: query: explain SELECT cbigint, cdouble FROM alltypesorc WHERE cbigint < cdouble and cint > 0 limit 7 +POSTHOOK: query: explain vectorization SELECT cbigint, cdouble FROM alltypesorc WHERE cbigint < cdouble and cint > 0 limit 7 POSTHOOK: type: QUERY +PLAN VECTORIZATION: + enabled: true + enabledConditionsMet: [hive.vectorized.execution.enabled IS true] + STAGE DEPENDENCIES: - Stage-0 is a root stage + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: alltypesorc + Statistics: Num rows: 12288 Data size: 183488 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((UDFToDouble(cbigint) < cdouble) and (cint > 0)) (type: boolean) + Statistics: Num rows: 1365 Data size: 20400 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: cbigint (type: bigint), cdouble (type: double) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1365 Data size: 16320 Basic stats: COMPLETE Column stats: COMPLETE + Limit + Number of rows: 7 + Statistics: Num rows: 7 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 7 Data size: 96 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 + Execution mode: vectorized, llap + LLAP IO: all inputs + Map Vectorization: + enabled: true + enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true + groupByVectorOutput: true + inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + allNative: false + usesVectorUDFAdaptor: false + vectorized: true + Stage: Stage-0 Fetch Operator limit: 7 Processor Tree: - TableScan - alias: alltypesorc - Filter Operator - predicate: ((UDFToDouble(cbigint) < cdouble) and (cint > 0)) (type: boolean) - Select Operator - expressions: cbigint (type: bigint), cdouble (type: double) - outputColumnNames: _col0, _col1 - Limit - Number of rows: 7 - ListSink + ListSink WARNING: Comparing a bigint and a double may result in a loss of precision. PREHOOK: query: SELECT cbigint, cdouble FROM alltypesorc WHERE cbigint < cdouble and cint > 0 limit 7 @@ -38,16 +71,16 @@ POSTHOOK: Input: default@alltypesorc -1887561756 -8881.0 -1887561756 -2281.0 -1887561756 9531.0 -PREHOOK: query: -- HIVE-3562 Some limit can be pushed down to map stage - c/p parts from limit_pushdown - -explain +PREHOOK: query: explain vectorization expression select ctinyint,cdouble,csmallint from alltypesorc where ctinyint is not null order by ctinyint,cdouble limit 20 PREHOOK: type: QUERY -POSTHOOK: query: -- HIVE-3562 Some limit can be pushed down to map stage - c/p parts from limit_pushdown - -explain +POSTHOOK: query: explain vectorization expression select ctinyint,cdouble,csmallint from alltypesorc where ctinyint is not null order by ctinyint,cdouble limit 20 POSTHOOK: type: QUERY +PLAN VECTORIZATION: + enabled: true + enabledConditionsMet: [hive.vectorized.execution.enabled IS true] + STAGE DEPENDENCIES: Stage-1 is a root stage Stage-0 depends on stages: Stage-1 @@ -55,6 +88,7 @@ STAGE DEPENDENCIES: STAGE PLANS: Stage: Stage-1 Tez +#### A masked pattern was here #### Edges: Reducer 2 <- Map 1 (SIMPLE_EDGE) #### A masked pattern was here #### @@ -63,37 +97,79 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 146796 Basic stats: COMPLETE Column stats: COMPLETE + TableScan Vectorization: + native: true + projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11] Filter Operator + Filter Vectorization: + className: VectorFilterOperator + native: true + predicateExpression: SelectColumnIsNotNull(col 0) -> boolean predicate: ctinyint is not null (type: boolean) - Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9173 Data size: 109584 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ctinyint (type: tinyint), cdouble (type: double), csmallint (type: smallint) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumns: [0, 5, 1] + Statistics: Num rows: 9173 Data size: 109584 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: tinyint), _col1 (type: double) sort order: ++ - Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE + Reduce Sink Vectorization: + className: VectorReduceSinkOperator + native: false + nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No buckets IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true + nativeConditionsNotMet: No TopN IS false, Uniform Hash IS false + Statistics: Num rows: 9173 Data size: 109584 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.3 value expressions: _col2 (type: smallint) Execution mode: vectorized, llap + LLAP IO: all inputs + Map Vectorization: + enabled: true + enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true + groupByVectorOutput: true + inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + allNative: false + usesVectorUDFAdaptor: false + vectorized: true Reducer 2 - Execution mode: vectorized, uber + Execution mode: vectorized, llap + Reduce Vectorization: + enabled: true + enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true + groupByVectorOutput: true + allNative: false + usesVectorUDFAdaptor: false + vectorized: true Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: tinyint), KEY.reducesinkkey1 (type: double), VALUE._col0 (type: smallint) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumns: [0, 1, 2] + Statistics: Num rows: 9173 Data size: 109584 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 20 - Statistics: Num rows: 20 Data size: 4300 Basic stats: COMPLETE Column stats: NONE + Limit Vectorization: + className: VectorLimitOperator + native: true + Statistics: Num rows: 20 Data size: 256 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 20 Data size: 4300 Basic stats: COMPLETE Column stats: NONE + File Sink Vectorization: + className: VectorFileSinkOperator + native: false + Statistics: Num rows: 20 Data size: 256 Basic stats: COMPLETE Column stats: COMPLETE table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 @@ -130,14 +206,16 @@ POSTHOOK: Input: default@alltypesorc -64 -2919.0 -2919 -64 -1600.0 -1600 -64 -200.0 -200 -PREHOOK: query: -- deduped RS -explain +PREHOOK: query: explain vectorization expression select ctinyint,avg(cdouble + 1) from alltypesorc group by ctinyint order by ctinyint limit 20 PREHOOK: type: QUERY -POSTHOOK: query: -- deduped RS -explain +POSTHOOK: query: explain vectorization expression select ctinyint,avg(cdouble + 1) from alltypesorc group by ctinyint order by ctinyint limit 20 POSTHOOK: type: QUERY +PLAN VECTORIZATION: + enabled: true + enabledConditionsMet: [hive.vectorized.execution.enabled IS true] + STAGE DEPENDENCIES: Stage-1 is a root stage Stage-0 depends on stages: Stage-1 @@ -145,6 +223,7 @@ STAGE DEPENDENCIES: STAGE PLANS: Stage: Stage-1 Tez +#### A masked pattern was here #### Edges: Reducer 2 <- Map 1 (SIMPLE_EDGE) #### A masked pattern was here #### @@ -153,43 +232,73 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 110096 Basic stats: COMPLETE Column stats: COMPLETE + TableScan Vectorization: + native: true + projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11] Select Operator expressions: ctinyint (type: tinyint), (cdouble + 1.0) (type: double) outputColumnNames: _col0, _col1 - Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumns: [0, 12] + selectExpressions: DoubleColAddDoubleScalar(col 5, val 1.0) -> 12:double + Statistics: Num rows: 12288 Data size: 110096 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: avg(_col1) + Group By Vectorization: + aggregators: VectorUDAFAvgDouble(col 12) -> struct + className: VectorGroupByOperator + vectorOutput: false + keyExpressions: col 0 + native: false + projectedOutputColumns: [0] + vectorOutputConditionsNotMet: Vector output of VectorUDAFAvgDouble(col 12) -> struct output type STRUCT requires PRIMITIVE IS false keys: _col0 (type: tinyint) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 95 Data size: 7888 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: tinyint) sort order: + Map-reduce partition columns: _col0 (type: tinyint) - Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 95 Data size: 7888 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.3 value expressions: _col1 (type: struct) Execution mode: vectorized, llap + LLAP IO: all inputs + Map Vectorization: + enabled: true + enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true + groupByVectorOutput: false + inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + allNative: false + usesVectorUDFAdaptor: false + vectorized: true Reducer 2 - Execution mode: uber + 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 UDF avg parameter expression for GROUPBY operator: Data type struct of Column[VALUE._col0] not supported + vectorized: false Reduce Operator Tree: Group By Operator aggregations: avg(VALUE._col0) keys: KEY._col0 (type: tinyint) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 95 Data size: 1048 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 20 - Statistics: Num rows: 20 Data size: 4300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 20 Data size: 4300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 @@ -226,14 +335,16 @@ NULL 9370.0945309795 -48 1672.909090909091 -47 -574.6428571428571 -46 3033.55 -PREHOOK: query: -- distincts -explain +PREHOOK: query: explain vectorization expression select distinct(ctinyint) from alltypesorc limit 20 PREHOOK: type: QUERY -POSTHOOK: query: -- distincts -explain +POSTHOOK: query: explain vectorization expression select distinct(ctinyint) from alltypesorc limit 20 POSTHOOK: type: QUERY +PLAN VECTORIZATION: + enabled: true + enabledConditionsMet: [hive.vectorized.execution.enabled IS true] + STAGE DEPENDENCIES: Stage-1 is a root stage Stage-0 depends on stages: Stage-1 @@ -241,6 +352,7 @@ STAGE DEPENDENCIES: STAGE PLANS: Stage: Stage-1 Tez +#### A masked pattern was here #### Edges: Reducer 2 <- Map 1 (SIMPLE_EDGE) #### A masked pattern was here #### @@ -249,40 +361,86 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 36696 Basic stats: COMPLETE Column stats: COMPLETE + TableScan Vectorization: + native: true + projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11] Select Operator expressions: ctinyint (type: tinyint) outputColumnNames: ctinyint - Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumns: [0] + Statistics: Num rows: 12288 Data size: 36696 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator + Group By Vectorization: + className: VectorGroupByOperator + vectorOutput: true + keyExpressions: col 0 + native: false + projectedOutputColumns: [] keys: ctinyint (type: tinyint) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 95 Data size: 288 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: tinyint) sort order: + Map-reduce partition columns: _col0 (type: tinyint) - Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE + Reduce Sink Vectorization: + className: VectorReduceSinkOperator + native: false + nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No buckets IS true, Uniform Hash IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true + nativeConditionsNotMet: No TopN IS false + Statistics: Num rows: 95 Data size: 288 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.3 Execution mode: vectorized, llap + LLAP IO: all inputs + Map Vectorization: + enabled: true + enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true + groupByVectorOutput: true + inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + allNative: false + usesVectorUDFAdaptor: false + vectorized: true Reducer 2 - Execution mode: vectorized, uber + Execution mode: vectorized, llap + Reduce Vectorization: + enabled: true + enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true + groupByVectorOutput: true + allNative: false + usesVectorUDFAdaptor: false + vectorized: true Reduce Operator Tree: Group By Operator + Group By Vectorization: + className: VectorGroupByOperator + vectorOutput: true + keyExpressions: col 0 + native: false + projectedOutputColumns: [] keys: KEY._col0 (type: tinyint) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 95 Data size: 288 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 20 - Statistics: Num rows: 20 Data size: 4300 Basic stats: COMPLETE Column stats: NONE + Limit Vectorization: + className: VectorLimitOperator + native: true + Statistics: Num rows: 20 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 20 Data size: 4300 Basic stats: COMPLETE Column stats: NONE + File Sink Vectorization: + className: VectorFileSinkOperator + native: false + Statistics: Num rows: 20 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 @@ -319,12 +477,16 @@ NULL -48 -47 -46 -PREHOOK: query: explain +PREHOOK: query: explain vectorization expression select ctinyint, count(distinct(cdouble)) from alltypesorc group by ctinyint order by ctinyint limit 20 PREHOOK: type: QUERY -POSTHOOK: query: explain +POSTHOOK: query: explain vectorization expression select ctinyint, count(distinct(cdouble)) from alltypesorc group by ctinyint order by ctinyint limit 20 POSTHOOK: type: QUERY +PLAN VECTORIZATION: + enabled: true + enabledConditionsMet: [hive.vectorized.execution.enabled IS true] + STAGE DEPENDENCIES: Stage-1 is a root stage Stage-0 depends on stages: Stage-1 @@ -332,6 +494,7 @@ STAGE DEPENDENCIES: STAGE PLANS: Stage: Stage-1 Tez +#### A masked pattern was here #### Edges: Reducer 2 <- Map 1 (SIMPLE_EDGE) #### A masked pattern was here #### @@ -340,45 +503,98 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 110096 Basic stats: COMPLETE Column stats: COMPLETE + TableScan Vectorization: + native: true + projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11] Select Operator expressions: ctinyint (type: tinyint), cdouble (type: double) outputColumnNames: ctinyint, cdouble - Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumns: [0, 5] + Statistics: Num rows: 12288 Data size: 110096 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator + Group By Vectorization: + className: VectorGroupByOperator + vectorOutput: true + keyExpressions: col 0, col 5 + native: false + projectedOutputColumns: [] keys: ctinyint (type: tinyint), cdouble (type: double) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 55052 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: tinyint), _col1 (type: double) sort order: ++ Map-reduce partition columns: _col0 (type: tinyint) - Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE + Reduce Sink Vectorization: + className: VectorReduceSinkOperator + native: false + nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No buckets IS true, No TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true + nativeConditionsNotMet: Uniform Hash IS false + Statistics: Num rows: 6144 Data size: 55052 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap + LLAP IO: all inputs + Map Vectorization: + enabled: true + enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true + groupByVectorOutput: true + inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + allNative: false + usesVectorUDFAdaptor: false + vectorized: true Reducer 2 - Execution mode: uber + Execution mode: vectorized, llap + Reduce Vectorization: + enabled: true + enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true + groupByVectorOutput: true + allNative: false + usesVectorUDFAdaptor: false + vectorized: true Reduce Operator Tree: Group By Operator + Group By Vectorization: + className: VectorGroupByOperator + vectorOutput: true + keyExpressions: col 0, col 1 + native: false + projectedOutputColumns: [] keys: KEY._col0 (type: tinyint), KEY._col1 (type: double) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 55052 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(_col1) + Group By Vectorization: + aggregators: VectorUDAFCount(col 1) -> bigint + className: VectorGroupByOperator + vectorOutput: true + keyExpressions: col 0 + native: false + projectedOutputColumns: [0] keys: _col0 (type: tinyint) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 3072 Data size: 660491 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 95 Data size: 1048 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 20 - Statistics: Num rows: 20 Data size: 4300 Basic stats: COMPLETE Column stats: NONE + Limit Vectorization: + className: VectorLimitOperator + native: true + Statistics: Num rows: 20 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 20 Data size: 4300 Basic stats: COMPLETE Column stats: NONE + File Sink Vectorization: + className: VectorFileSinkOperator + native: false + Statistics: Num rows: 20 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 @@ -415,14 +631,16 @@ NULL 2932 -48 29 -47 22 -46 24 -PREHOOK: query: -- limit zero -explain +PREHOOK: query: explain vectorization expression select ctinyint,cdouble from alltypesorc order by ctinyint limit 0 PREHOOK: type: QUERY -POSTHOOK: query: -- limit zero -explain +POSTHOOK: query: explain vectorization expression select ctinyint,cdouble from alltypesorc order by ctinyint limit 0 POSTHOOK: type: QUERY +PLAN VECTORIZATION: + enabled: true + enabledConditionsMet: [hive.vectorized.execution.enabled IS true] + STAGE DEPENDENCIES: Stage-0 is a root stage @@ -441,14 +659,16 @@ POSTHOOK: query: select ctinyint,cdouble from alltypesorc order by ctinyint limi POSTHOOK: type: QUERY POSTHOOK: Input: default@alltypesorc #### A masked pattern was here #### -PREHOOK: query: -- 2MR (applied to last RS) -explain +PREHOOK: query: explain vectorization expression select cdouble, sum(ctinyint) as sum from alltypesorc where ctinyint is not null group by cdouble order by sum, cdouble limit 20 PREHOOK: type: QUERY -POSTHOOK: query: -- 2MR (applied to last RS) -explain +POSTHOOK: query: explain vectorization expression select cdouble, sum(ctinyint) as sum from alltypesorc where ctinyint is not null group by cdouble order by sum, cdouble limit 20 POSTHOOK: type: QUERY +PLAN VECTORIZATION: + enabled: true + enabledConditionsMet: [hive.vectorized.execution.enabled IS true] + STAGE DEPENDENCIES: Stage-1 is a root stage Stage-0 depends on stages: Stage-1 @@ -456,6 +676,7 @@ STAGE DEPENDENCIES: STAGE PLANS: Stage: Stage-1 Tez +#### A masked pattern was here #### Edges: Reducer 2 <- Map 1 (SIMPLE_EDGE) Reducer 3 <- Reducer 2 (SIMPLE_EDGE) @@ -465,57 +686,124 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 110096 Basic stats: COMPLETE Column stats: COMPLETE + TableScan Vectorization: + native: true + projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11] Filter Operator + Filter Vectorization: + className: VectorFilterOperator + native: true + predicateExpression: SelectColumnIsNotNull(col 0) -> boolean predicate: ctinyint is not null (type: boolean) - Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9173 Data size: 82188 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cdouble (type: double), ctinyint (type: tinyint) outputColumnNames: cdouble, ctinyint - Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumns: [5, 0] + Statistics: Num rows: 9173 Data size: 82188 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(ctinyint) + Group By Vectorization: + aggregators: VectorUDAFSumLong(col 0) -> bigint + className: VectorGroupByOperator + vectorOutput: true + keyExpressions: col 5 + native: false + projectedOutputColumns: [0] keys: cdouble (type: double) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3185 Data size: 44512 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: double) sort order: + Map-reduce partition columns: _col0 (type: double) - Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE + Reduce Sink Vectorization: + className: VectorReduceSinkMultiKeyOperator + native: true + nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No buckets IS true, No TopN IS true, Uniform Hash IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true + Statistics: Num rows: 3185 Data size: 44512 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Execution mode: vectorized, llap + LLAP IO: all inputs + Map Vectorization: + enabled: true + enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true + groupByVectorOutput: true + inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + allNative: false + usesVectorUDFAdaptor: false + vectorized: true Reducer 2 Execution mode: vectorized, llap + Reduce Vectorization: + enabled: true + enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true + groupByVectorOutput: true + allNative: false + usesVectorUDFAdaptor: false + vectorized: true Reduce Operator Tree: Group By Operator aggregations: sum(VALUE._col0) + Group By Vectorization: + aggregators: VectorUDAFSumLong(col 1) -> bigint + className: VectorGroupByOperator + vectorOutput: true + keyExpressions: col 0 + native: false + projectedOutputColumns: [0] keys: KEY._col0 (type: double) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 3072 Data size: 660491 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3185 Data size: 44512 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: bigint), _col0 (type: double) sort order: ++ - Statistics: Num rows: 3072 Data size: 660491 Basic stats: COMPLETE Column stats: NONE + Reduce Sink Vectorization: + className: VectorReduceSinkOperator + native: false + nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No buckets IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true + nativeConditionsNotMet: No TopN IS false, Uniform Hash IS false + Statistics: Num rows: 3185 Data size: 44512 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.3 Reducer 3 - Execution mode: vectorized, uber + Execution mode: vectorized, llap + Reduce Vectorization: + enabled: true + enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true + groupByVectorOutput: true + allNative: false + usesVectorUDFAdaptor: false + vectorized: true Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey1 (type: double), KEY.reducesinkkey0 (type: bigint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 3072 Data size: 660491 Basic stats: COMPLETE Column stats: NONE + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumns: [1, 0] + Statistics: Num rows: 3185 Data size: 44512 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 20 - Statistics: Num rows: 20 Data size: 4300 Basic stats: COMPLETE Column stats: NONE + Limit Vectorization: + className: VectorLimitOperator + native: true + Statistics: Num rows: 20 Data size: 288 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 20 Data size: 4300 Basic stats: COMPLETE Column stats: NONE + File Sink Vectorization: + className: VectorFileSinkOperator + native: false + Statistics: Num rows: 20 Data size: 288 Basic stats: COMPLETE Column stats: COMPLETE table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 diff --git ql/src/test/results/clientpositive/llap/vectorization_offset_limit.q.out ql/src/test/results/clientpositive/llap/vectorization_offset_limit.q.out index d5a1f47..8be0cac 100644 --- ql/src/test/results/clientpositive/llap/vectorization_offset_limit.q.out +++ ql/src/test/results/clientpositive/llap/vectorization_offset_limit.q.out @@ -118,7 +118,7 @@ STAGE PLANS: Reduce Sink Vectorization: className: VectorReduceSinkOperator native: false - nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, Not ACID UPDATE or DELETE IS true, No buckets IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true + nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No buckets IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: No TopN IS false, Uniform Hash IS false Statistics: Num rows: 9173 Data size: 109584 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 diff --git ql/src/test/results/clientpositive/llap/vectorized_mapjoin2.q.out ql/src/test/results/clientpositive/llap/vectorized_mapjoin2.q.out index 7621cbe..fbe0b6c 100644 --- ql/src/test/results/clientpositive/llap/vectorized_mapjoin2.q.out +++ ql/src/test/results/clientpositive/llap/vectorized_mapjoin2.q.out @@ -103,7 +103,7 @@ STAGE PLANS: Reduce Sink Vectorization: className: VectorReduceSinkOperator native: false - nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, Not ACID UPDATE or DELETE IS true, No buckets IS true, No TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true + nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No buckets IS true, No TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: Uniform Hash IS false Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint) @@ -147,7 +147,7 @@ STAGE PLANS: Reduce Sink Vectorization: className: VectorReduceSinkLongOperator native: true - nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, Not ACID UPDATE or DELETE IS true, No buckets IS true, No TopN IS true, Uniform Hash IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true + nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No buckets IS true, No TopN IS true, Uniform Hash IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true Statistics: Num rows: 45 Data size: 181 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized, llap LLAP IO: all inputs diff --git ql/src/test/results/clientpositive/vector_char_2.q.out ql/src/test/results/clientpositive/vector_char_2.q.out index 8c5dd3e..adfd5f0 100644 --- ql/src/test/results/clientpositive/vector_char_2.q.out +++ ql/src/test/results/clientpositive/vector_char_2.q.out @@ -85,7 +85,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [1, 2] - selectExpressions: VectorUDFAdaptor(UDFToInteger(key)) -> 2:int + selectExpressions: CastStringToLong(col 0) -> 2:int Statistics: Num rows: 500 Data size: 99000 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: sum(_col1), count() @@ -119,7 +119,7 @@ STAGE PLANS: groupByVectorOutput: true inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat allNative: false - usesVectorUDFAdaptor: true + usesVectorUDFAdaptor: false vectorized: true Reduce Vectorization: enabled: false @@ -263,7 +263,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [1, 2] - selectExpressions: VectorUDFAdaptor(UDFToInteger(key)) -> 2:int + selectExpressions: CastStringToLong(col 0) -> 2:int Statistics: Num rows: 500 Data size: 99000 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: sum(_col1), count() @@ -297,7 +297,7 @@ STAGE PLANS: groupByVectorOutput: true inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat allNative: false - usesVectorUDFAdaptor: true + usesVectorUDFAdaptor: false vectorized: true Reduce Vectorization: enabled: false diff --git ql/src/test/results/clientpositive/vector_coalesce_2.q.out ql/src/test/results/clientpositive/vector_coalesce_2.q.out index 12d1aaa..1518235 100644 --- ql/src/test/results/clientpositive/vector_coalesce_2.q.out +++ ql/src/test/results/clientpositive/vector_coalesce_2.q.out @@ -198,7 +198,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [1, 4] - selectExpressions: VectorUDFAdaptor(UDFToInteger(COALESCE(str1,0)))(children: VectorCoalesce(columns [0, 2])(children: col 0, ConstantVectorExpression(val 0) -> 2:string) -> 3:string) -> 4:int + selectExpressions: CastStringToLong(col 3)(children: VectorCoalesce(columns [0, 2])(children: col 0, ConstantVectorExpression(val 0) -> 2:string) -> 3:string) -> 4:int Statistics: Num rows: 4 Data size: 510 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: sum(_col1) @@ -231,7 +231,7 @@ STAGE PLANS: groupByVectorOutput: true inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat allNative: false - usesVectorUDFAdaptor: true + usesVectorUDFAdaptor: false vectorized: true Reduce Vectorization: enabled: false