Github user tdas commented on a diff in the pull request: https://github.com/apache/spark/pull/20828#discussion_r179603916 --- Diff: sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/continuous/ContinuousMemoryStream.scala --- @@ -0,0 +1,212 @@ +/* + * 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.continuous + +import java.{util => ju} +import java.util.Optional +import java.util.concurrent.ArrayBlockingQueue +import javax.annotation.concurrent.GuardedBy + +import scala.collection.JavaConverters._ +import scala.collection.mutable.ListBuffer +import scala.reflect.ClassTag + +import org.json4s.NoTypeHints +import org.json4s.jackson.Serialization + +import org.apache.spark.SparkEnv +import org.apache.spark.internal.Logging +import org.apache.spark.rpc.{RpcCallContext, RpcEndpointRef, RpcEnv, ThreadSafeRpcEndpoint} +import org.apache.spark.sql.{Dataset, Encoder, Row, SQLContext} +import org.apache.spark.sql.catalyst.encoders.encoderFor +import org.apache.spark.sql.catalyst.expressions.UnsafeRow +import org.apache.spark.sql.execution.streaming._ +import org.apache.spark.sql.sources.v2.{ContinuousReadSupport, DataSourceOptions} +import org.apache.spark.sql.sources.v2.reader.{DataReader, DataReaderFactory, SupportsScanUnsafeRow} +import org.apache.spark.sql.sources.v2.reader.streaming.{ContinuousDataReader, ContinuousReader, Offset, PartitionOffset} +import org.apache.spark.sql.types.StructType +import org.apache.spark.util.RpcUtils + +/** + * The overall strategy here is: + * * ContinuousMemoryStream maintains a list of records for each partition. addData() will + * distribute records evenly-ish across partitions. + * * ContinuousMemoryStreamRecordBuffer is set up as an endpoint for partition-level + * ContinuousMemoryStreamDataReader 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. + */ + +private case class GetRecord(offset: ContinuousMemoryStreamPartitionOffset) --- End diff -- nit: I generally put such small-use generically-named classes inside a relevant object to avoid cluttering of the general class namespace. Example: this can be inside a object ContinuousMemoryStreamRecordBuffer as that is the only one using it. Then when someone searches for a different GetRecord-ish named class, then it would be less confusing.
--- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org