anishshri-db commented on code in PR #45674: URL: https://github.com/apache/spark/pull/45674#discussion_r1541540920
########## sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/StateVariableWithTTLSupport.scala: ########## @@ -0,0 +1,187 @@ +/* + * 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.time.Duration + +import org.apache.spark.internal.Logging +import org.apache.spark.sql.catalyst.InternalRow +import org.apache.spark.sql.catalyst.expressions.UnsafeProjection +import org.apache.spark.sql.execution.streaming.state.{NoPrefixKeyStateEncoderSpec, StateStore} +import org.apache.spark.sql.streaming.TTLMode +import org.apache.spark.sql.types.{BinaryType, DataType, LongType, NullType, StructField, StructType} + +object StateTTLSchema { + val KEY_ROW_SCHEMA: StructType = new StructType() + .add("expirationMs", LongType) + .add("groupingKey", BinaryType) + val VALUE_ROW_SCHEMA: StructType = + StructType(Array(StructField("__dummy__", NullType))) +} + +/** + * Encapsulates the ttl row information stored in [[SingleKeyTTLState]]. + * @param groupingKey grouping key for which ttl is set + * @param expirationMs expiration time for the grouping key + */ +case class SingleKeyTTLRow( + groupingKey: Array[Byte], + expirationMs: Long) + +/** + * Represents a State variable which supports TTL. + */ +trait StateVariableWithTTLSupport { + + /** + * Clears the user state associated with this grouping key + * if it has expired. This function is called by Spark to perform + * cleanup at the end of transformWithState processing. + * + * Spark uses a secondary index to determine if the user state for + * this grouping key has expired. However, its possible that the user + * has updated the TTL and secondary index is out of date. Implementations + * must validate that the user State has actually expired before cleanup based + * on their own State data. + * + * @param groupingKey grouping key for which cleanup should be performed. + */ + def clearIfExpired(groupingKey: Array[Byte]): Unit +} + +/** + * Represents the underlying state for secondary TTL Index for a user defined + * state variable. + * + * This state allows Spark to query ttl values based on expiration time + * allowing efficient ttl cleanup. + */ +trait TTLState { + + /** + * Perform the user state clean yp based on ttl values stored in Review Comment: nit: `Perform the user state clean up based` -- 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
