rangadi commented on code in PR #41146: URL: https://github.com/apache/spark/pull/41146#discussion_r1228848876
########## connector/connect/server/src/main/scala/org/apache/spark/sql/connect/service/SparkConnectCachedDataFrameManager.scala: ########## @@ -0,0 +1,62 @@ +/* + * 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 given ids. The Spark Connect client can + * create a DataFrame reference with the id. 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, dataFrameId: String, value: DataFrame): Unit = + synchronized { + val sessionKey = (userId, sessionId) + val sessionDataFrameMap = dataFrameCache + .getOrElseUpdate(sessionKey, mutable.Map[String, DataFrame]()) + sessionDataFrameMap.put(dataFrameId, value) + } Review Comment: Agree, we could user ConcurrentHashMap. But I often end up preferring `synchronized` as well. Since this is not perf critical (used only for certain DFs), though I am not sure if there is any perf difference. Added `@GuardedBy` annotation. See the the continuation of this PR here: https://github.com/apache/spark/pull/41580/files#diff-1a8933e9723f5497c3991441c7ff21fe43db63d483354af9a0113043ea600b3eR42 ########## connector/connect/server/src/main/scala/org/apache/spark/sql/connect/service/SparkConnectCachedDataFrameManager.scala: ########## @@ -0,0 +1,62 @@ +/* + * 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 given ids. The Spark Connect client can + * create a DataFrame reference with the id. 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 { Review Comment: Discussed above. SessionHolder is not accessible yet. Also removed session_id and user_id from this cache, instead making it key on actual Spark session (user_id & session_id is implicit in that) ########## connector/connect/server/src/main/scala/org/apache/spark/sql/connect/planner/SparkConnectPlanner.scala: ########## @@ -786,6 +788,12 @@ class SparkConnectPlanner(val session: SparkSession) { .logicalPlan } + private def transformCachedRemoteRelation(rel: proto.CachedRemoteRelation): LogicalPlan = { + SparkConnectService.cachedDataFrameManager + .get(rel.getUserId, rel.getSessionId, rel.getRelationId) + .logicalPlan + } Review Comment: Agree. For now proposing to keep it in separate class. Continue discussion [here](https://github.com/apache/spark/pull/41580#discussion_r1228842072). ########## connector/connect/server/src/main/scala/org/apache/spark/sql/connect/service/SparkConnectCachedDataFrameManager.scala: ########## @@ -0,0 +1,62 @@ +/* + * 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 given ids. The Spark Connect client can + * create a DataFrame reference with the id. 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 { Review Comment: Removed. See continuation of this PR : #41580 ########## python/pyspark/sql/connect/session.py: ########## @@ -476,6 +476,11 @@ def createDataFrame( createDataFrame.__doc__ = PySparkSession.createDataFrame.__doc__ + def _createCachedDataFrame(self, relationId: str) -> "DataFrame": Review Comment: Removed. It will used in foreachBatch implementation (in follow up PRs) ########## connector/connect/common/src/main/protobuf/spark/connect/relations.proto: ########## @@ -395,6 +396,18 @@ message CachedLocalRelation { string hash = 3; } +// Represents a remote relation that has been cached on server. +message CachedRemoteRelation { + // (Required) An identifier of the user which cached the relation + string userId = 1; + + // (Required) An identifier of the Spark session in which the relation is cached + string sessionId = 2; Review Comment: Agree. This is important. Changed the implementation to use SparkSession as the key (it has as `sessionUUID`) [continue the discussion [here](https://github.com/apache/spark/pull/41580#discussion_r1228837983)] -- 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]
