RussellSpitzer commented on a change in pull request #3983: URL: https://github.com/apache/iceberg/pull/3983#discussion_r830101082
########## File path: spark/v3.2/spark/src/main/java/org/apache/iceberg/spark/actions/Spark3ZOrderUDF.java ########## @@ -0,0 +1,239 @@ +/* + * 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.iceberg.spark.actions; + +import java.io.IOException; +import java.io.Serializable; +import java.nio.ByteBuffer; +import java.nio.charset.CharsetEncoder; +import java.nio.charset.StandardCharsets; +import org.apache.iceberg.util.ZOrderByteUtils; +import org.apache.spark.sql.Column; +import org.apache.spark.sql.expressions.UserDefinedFunction; +import org.apache.spark.sql.functions; +import org.apache.spark.sql.types.BinaryType; +import org.apache.spark.sql.types.BooleanType; +import org.apache.spark.sql.types.ByteType; +import org.apache.spark.sql.types.DataType; +import org.apache.spark.sql.types.DataTypes; +import org.apache.spark.sql.types.DateType; +import org.apache.spark.sql.types.DoubleType; +import org.apache.spark.sql.types.FloatType; +import org.apache.spark.sql.types.IntegerType; +import org.apache.spark.sql.types.LongType; +import org.apache.spark.sql.types.ShortType; +import org.apache.spark.sql.types.StringType; +import org.apache.spark.sql.types.TimestampType; +import scala.collection.Seq; + +class Spark3ZOrderUDF implements Serializable { + private static final int STRING_KEY_LENGTH = 16; + + private static final byte[] PRIMITIVE_EMPTY = new byte[ZOrderByteUtils.BUFFER_SIZE]; + + private transient ThreadLocal<ByteBuffer> outputBuffer; + private transient ThreadLocal<byte[][]> inputHolder; + private transient ThreadLocal<ByteBuffer>[] inputBuffers; + private transient ThreadLocal<CharsetEncoder> encoder; + + private final int numCols; + + private int inputCol = 0; + private int totalBytes = 0; + + Spark3ZOrderUDF(int numCols) { + this.numCols = numCols; + } + + private void readObject(java.io.ObjectInputStream in) + throws IOException, ClassNotFoundException { + in.defaultReadObject(); + inputBuffers = new ThreadLocal[numCols]; + inputHolder = ThreadLocal.withInitial(() -> new byte[numCols][]); + encoder = ThreadLocal.withInitial(() -> StandardCharsets.UTF_8.newEncoder()); + } + + private ByteBuffer outputBuffer(int size) { + if (outputBuffer == null) { Review comment: Yeah no reason we couldn't set it in readObject, I think I just initially put it here before I had implemented the other buffers. As for thread execution, the way we generate the UDF means that you get a single "outputBuffer" for every thread. The way Spark should be running this is with a single thread per execution context (task) which means that any individual invocation should actually be in serial. That's why we don't have any protections on any of these buffer references. -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: [email protected] For queries about this service, please contact Infrastructure at: [email protected] --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
