viirya commented on code in PR #52502: URL: https://github.com/apache/spark/pull/52502#discussion_r2433343385
########## sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/sources/LowLatencyMemoryStream.scala: ########## @@ -0,0 +1,300 @@ +/* + * 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.streaming + +import java.util.concurrent.atomic.AtomicInteger +import javax.annotation.concurrent.GuardedBy + +import scala.collection.mutable.ListBuffer + +import org.json4s.{Formats, NoTypeHints} +import org.json4s.jackson.Serialization + +import org.apache.spark.{SparkEnv, TaskContext} +import org.apache.spark.rpc.{RpcAddress, RpcEndpointRef} +import org.apache.spark.sql.{Encoder, SQLContext} +import org.apache.spark.sql.catalyst.InternalRow +import org.apache.spark.sql.catalyst.expressions.UnsafeRow +import org.apache.spark.sql.connector.read.InputPartition +import org.apache.spark.sql.connector.read.PartitionReader +import org.apache.spark.sql.connector.read.PartitionReaderFactory +import org.apache.spark.sql.connector.read.streaming.{ + Offset => OffsetV2, + PartitionOffset, + ReadLimit, + SupportsRealTimeMode, + SupportsRealTimeRead +} +import org.apache.spark.sql.connector.read.streaming.SupportsRealTimeRead.RecordStatus +import org.apache.spark.sql.execution.datasources.v2.LowLatencyClock +import org.apache.spark.sql.execution.streaming.runtime._ +import org.apache.spark.util.{Clock, RpcUtils} + +/** + * A low latency memory source from memory, only for unit test purpose. + * This class is very similar to ContinuousMemoryStream, except that it implements the + * interface of SupportsRealTimeMode, rather than ContinuousStream + * The overall strategy here is: + * * LowLatencyMemoryStream maintains a list of records for each partition. addData() will + * distribute records evenly-ish across partitions. + * * RecordEndpoint is set up as an endpoint for executor-side + * LowLatencyMemoryStreamInputPartitionReader instances to poll. It returns the record at + * the specified offset within the list, or null if that offset doesn't yet have a record. + */ +class LowLatencyMemoryStream[A: Encoder]( + id: Int, + sqlContext: SQLContext, + numPartitions: Int = 2, + clock: Clock = LowLatencyClock.getClock) + extends MemoryStreamBaseClass[A](0, sqlContext) + with SupportsRealTimeMode { + private implicit val formats: Formats = Serialization.formats(NoTypeHints) + + // LowLatencyReader implementation Review Comment: Is this comment supposed to be here? Seems unrelated to the code. -- 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]
