spark-reviews mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From dongjoon-hyun <...@git.apache.org>
Subject [GitHub] spark pull request #19943: [SPARK-16060][SQL] Support Vectorized ORC Reader
Date Tue, 09 Jan 2018 05:51:50 GMT
Github user dongjoon-hyun commented on a diff in the pull request:

    https://github.com/apache/spark/pull/19943#discussion_r160323569
  
    --- Diff: sql/core/src/main/java/org/apache/spark/sql/execution/datasources/orc/OrcColumnarBatchReader.java
---
    @@ -0,0 +1,605 @@
    +/*
    + * 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.spark.sql.execution.datasources.orc;
    +
    +import java.io.IOException;
    +import java.util.stream.IntStream;
    +
    +import org.apache.hadoop.conf.Configuration;
    +import org.apache.hadoop.mapreduce.InputSplit;
    +import org.apache.hadoop.mapreduce.RecordReader;
    +import org.apache.hadoop.mapreduce.TaskAttemptContext;
    +import org.apache.hadoop.mapreduce.lib.input.FileSplit;
    +import org.apache.orc.OrcConf;
    +import org.apache.orc.OrcFile;
    +import org.apache.orc.Reader;
    +import org.apache.orc.TypeDescription;
    +import org.apache.orc.mapred.OrcInputFormat;
    +import org.apache.orc.storage.common.type.HiveDecimal;
    +import org.apache.orc.storage.ql.exec.vector.*;
    +import org.apache.orc.storage.serde2.io.HiveDecimalWritable;
    +
    +import org.apache.spark.memory.MemoryMode;
    +import org.apache.spark.sql.catalyst.InternalRow;
    +import org.apache.spark.sql.execution.vectorized.ColumnVectorUtils;
    +import org.apache.spark.sql.execution.vectorized.OffHeapColumnVector;
    +import org.apache.spark.sql.execution.vectorized.OnHeapColumnVector;
    +import org.apache.spark.sql.execution.vectorized.WritableColumnVector;
    +import org.apache.spark.sql.types.*;
    +import org.apache.spark.sql.vectorized.ColumnarBatch;
    +
    +
    +/**
    + * To support vectorization in WholeStageCodeGen, this reader returns ColumnarBatch.
    + * After creating, `initialize` and `initBatch` should be called sequentially.
    + */
    +public class OrcColumnarBatchReader extends RecordReader<Void, ColumnarBatch> {
    +  /**
    +   * The default size of batch. We use this value for both ORC and Spark consistently
    +   * because they have different default values like the following.
    +   *
    +   * - ORC's VectorizedRowBatch.DEFAULT_SIZE = 1024
    +   * - Spark's ColumnarBatch.DEFAULT_BATCH_SIZE = 4 * 1024
    +   */
    +  public static final int DEFAULT_SIZE = 4 * 1024;
    +
    +  /**
    +   * Returns the number of micros since epoch from an element of TimestampColumnVector.
    +   */
    +  private static long fromTimestampColumnVector(TimestampColumnVector vector, int index)
{
    +    return vector.time[index] * 1000L + vector.nanos[index] / 1000L;
    +  }
    +
    +  // ORC File Reader
    +  private Reader reader;
    +
    +  // Vectorized ORC Row Batch
    +  private VectorizedRowBatch batch;
    +
    +  /**
    +   * The column IDs of the physical ORC file schema which are required by this reader.
    +   * -1 means this required column doesn't exist in the ORC file.
    +   */
    +  private int[] requestedColIds;
    +
    +  // Record reader from ORC row batch.
    +  private org.apache.orc.RecordReader recordReader;
    +
    +  private StructField[] requiredFields;
    +
    +  // The result columnar batch for vectorized execution by whole-stage codegen.
    +  private ColumnarBatch columnarBatch;
    +
    +  // Writable column vectors of the result columnar batch.
    +  private WritableColumnVector[] columnVectors;
    +
    +  // The number of rows read and considered to be returned.
    +  private long rowsReturned = 0L;
    +
    +  private long totalRowCount = 0L;
    --- End diff --
    
    Right. We can remove them.


---

---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org


Mime
View raw message