rangadi commented on code in PR #41146: URL: https://github.com/apache/spark/pull/41146#discussion_r1223516152
########## connector/connect/server/src/main/scala/org/apache/spark/sql/connect/service/SparkConnectCachedDataFrameManager.scala: ########## @@ -0,0 +1,61 @@ +/* + * 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.connect.service + +import scala.collection.mutable + +import org.apache.spark.internal.Logging +import org.apache.spark.sql.DataFrame +import org.apache.spark.sql.connect.common.InvalidPlanInput + +/** + * This class caches DataFrame on the server side with a given key as id. The Spark Connect client + * can create a DataFrame reference with the key. When server transforms the DataFrame reference, + * it finds the DataFrame from the cache and replace the reference. + * + * Each (userId, sessionId) has a corresponding DataFrame map. A cached DataFrame can only be + * accessed from the same user within the same session. The DataFrame will be removed from the cache + * when the session expires. + */ +private[connect] class SparkConnectCachedDataFrameManager extends Logging { + + // Each (userId, sessionId) has a DataFrame cache map. + private val dataFrameCache = mutable.Map[(String, String), mutable.Map[String, DataFrame]]() + + def put(userId: String, sessionId: String, key: String, value: DataFrame): Unit = synchronized { Review Comment: Better to rename `key` as `dataFrameId`. ########## connector/connect/common/src/main/protobuf/spark/connect/relations.proto: ########## @@ -394,6 +395,18 @@ message CachedLocalRelation { string hash = 3; } +// Represents a DataFrame that has been cached on server. +message CachedDataFrame { Review Comment: How about renaming this `CachedRemoteRelation`? DataFrame is an API level concept. ########## connector/connect/common/src/main/protobuf/spark/connect/relations.proto: ########## @@ -394,6 +395,18 @@ message CachedLocalRelation { string hash = 3; } +// Represents a DataFrame that has been cached on server. +message CachedDataFrame { + // (Required) An identifier of the user which cached the dataframe + string userId = 1; + + // (Required) An identifier of the Spark session in which the dataframe is cached + string sessionId = 2; + + // (Required) A key represents the id of the cached dataframe + string key = 3; Review Comment: Better to rename this as `id`, `relationId`, or `remoteId`. -- 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]
