MaxNevermind commented on code in PR #44636: URL: https://github.com/apache/spark/pull/44636#discussion_r1448235937
########## sql/catalyst/src/main/java/org/apache/spark/sql/connector/read/streaming/ReadLimit.java: ########## @@ -39,6 +39,8 @@ static ReadLimit minRows(long rows, long maxTriggerDelayMs) { static ReadLimit maxFiles(int files) { return new ReadMaxFiles(files); } + static ReadLimit maxBytes(int bytes) { return new ReadMaxBytes(bytes); } Review Comment: fixed ########## sql/catalyst/src/main/java/org/apache/spark/sql/connector/read/streaming/ReadMaxBytes.java: ########## @@ -0,0 +1,56 @@ +/* + * 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.connector.read.streaming; + +import org.apache.spark.annotation.Evolving; + +/** + * Represents a {@link ReadLimit} where the {@link MicroBatchStream} should scan files which total + * size doesn't go beyond a given maximum total size. Always reads at least one file so a stream + * can make progress in case of a file larger than a given maximum. + * + * @see SupportsAdmissionControl#latestOffset(Offset, ReadLimit) + * @since 4.0.0 + */ +@Evolving +public class ReadMaxBytes implements ReadLimit { + private int bytes; Review Comment: fixed ########## sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/FileStreamSource.scala: ########## @@ -113,16 +117,32 @@ class FileStreamSource( // Visible for testing and debugging in production. val seenFiles = new SeenFilesMap(maxFileAgeMs, fileNameOnly) - private var allFilesForTriggerAvailableNow: Seq[(SparkPath, Long)] = _ + private var allFilesForTriggerAvailableNow: Seq[NewFileEntry] = _ metadataLog.restore().foreach { entry => seenFiles.add(entry.sparkPath, entry.timestamp) } seenFiles.purge() - logInfo(s"maxFilesPerBatch = $maxFilesPerBatch, maxFileAgeMs = $maxFileAgeMs") + logInfo(s"maxFilesPerBatch = $maxFilesPerBatch, " + + s"maxBytesPerBatch = $maxBytesPerBatch, maxFileAgeMs = $maxFileAgeMs") + + private var unreadFiles: Seq[NewFileEntry] = _ - private var unreadFiles: Seq[(SparkPath, Long)] = _ + /** + * Split files into a selected/unselected pair according to a total size threshold. Review Comment: fixed -- 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