JiexingLi commented on code in PR #50230: URL: https://github.com/apache/spark/pull/50230#discussion_r2050969449
########## core/src/main/java/org/apache/spark/shuffle/checksum/RowBasedChecksum.scala: ########## @@ -0,0 +1,125 @@ +/* + * 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.shuffle.checksum + +import java.io.{ByteArrayOutputStream, ObjectOutputStream} +import java.util.zip.Checksum + +import scala.util.control.NonFatal + +import org.apache.spark.internal.Logging +import org.apache.spark.network.shuffle.checksum.ShuffleChecksumHelper + +/** + * A class for computing checksum for input (key, value) pairs. The checksum is independent of + * the order of the input (key, value) pairs. It is done by computing a checksum for each row + * first, and then computing the XOR for all the row checksums. + */ +abstract class RowBasedChecksum() extends Serializable with Logging { + private var hasError: Boolean = false + private var checksumValue: Long = 0 + /** Returns the checksum value computed. Tt returns the default checksum value (0) if there + * are any errors encountered during the checksum computation. + */ + def getValue: Long = { + if (!hasError) checksumValue else 0 + } + + /** Updates the row-based checksum with the given (key, value) pair */ + def update(key: Any, value: Any): Unit = { + if (!hasError) { + try { + val rowChecksumValue = calculateRowChecksum(key, value) + checksumValue = checksumValue ^ rowChecksumValue + } catch { + case NonFatal(e) => + logInfo("Checksum computation encountered error: ", e) + hasError = true + } + } + } + + /** Computes and returns the checksum value for the given (key, value) pair */ + protected def calculateRowChecksum(key: Any, value: Any): Long +} + +/** + * A Concrete implementation of RowBasedChecksum. The checksum for each row is + * computed by first converting the (key, value) pair to byte array using OutputStreams, + * and then computing the checksum for the byte array. + * + * @param checksumAlgorithm the algorithm used for computing checksum. + */ +class OutputStreamRowBasedChecksum(checksumAlgorithm: String) + extends RowBasedChecksum() { + + /** Subclass of ByteArrayOutputStream that exposes `buf` directly. */ + final private class MyByteArrayOutputStream(size: Int) + extends ByteArrayOutputStream(size) { + def getBuf: Array[Byte] = buf + } Review Comment: Can you help pointing me to where is it? This class is only used in test. ########## core/src/main/java/org/apache/spark/shuffle/checksum/RowBasedChecksum.scala: ########## @@ -0,0 +1,125 @@ +/* + * 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.shuffle.checksum + +import java.io.{ByteArrayOutputStream, ObjectOutputStream} +import java.util.zip.Checksum + +import scala.util.control.NonFatal + +import org.apache.spark.internal.Logging +import org.apache.spark.network.shuffle.checksum.ShuffleChecksumHelper + +/** + * A class for computing checksum for input (key, value) pairs. The checksum is independent of + * the order of the input (key, value) pairs. It is done by computing a checksum for each row + * first, and then computing the XOR for all the row checksums. + */ +abstract class RowBasedChecksum() extends Serializable with Logging { + private var hasError: Boolean = false + private var checksumValue: Long = 0 + /** Returns the checksum value computed. Tt returns the default checksum value (0) if there + * are any errors encountered during the checksum computation. + */ + def getValue: Long = { + if (!hasError) checksumValue else 0 + } + + /** Updates the row-based checksum with the given (key, value) pair */ + def update(key: Any, value: Any): Unit = { + if (!hasError) { + try { + val rowChecksumValue = calculateRowChecksum(key, value) + checksumValue = checksumValue ^ rowChecksumValue + } catch { + case NonFatal(e) => + logInfo("Checksum computation encountered error: ", e) + hasError = true + } + } + } + + /** Computes and returns the checksum value for the given (key, value) pair */ + protected def calculateRowChecksum(key: Any, value: Any): Long +} + +/** + * A Concrete implementation of RowBasedChecksum. The checksum for each row is + * computed by first converting the (key, value) pair to byte array using OutputStreams, + * and then computing the checksum for the byte array. + * + * @param checksumAlgorithm the algorithm used for computing checksum. + */ +class OutputStreamRowBasedChecksum(checksumAlgorithm: String) + extends RowBasedChecksum() { + + /** Subclass of ByteArrayOutputStream that exposes `buf` directly. */ + final private class MyByteArrayOutputStream(size: Int) + extends ByteArrayOutputStream(size) { + def getBuf: Array[Byte] = buf + } Review Comment: Done -- 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: reviews-unsubscr...@spark.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org
