bvarghese1 commented on code in PR #26424: URL: https://github.com/apache/flink/pull/26424#discussion_r2036575201
########## flink-table/flink-table-runtime/src/main/java/org/apache/flink/table/runtime/operators/over/NonTimeRowsUnboundedPrecedingFunction.java: ########## @@ -0,0 +1,719 @@ +/* + * 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.flink.table.runtime.operators.over; + +import org.apache.flink.annotation.VisibleForTesting; +import org.apache.flink.api.common.functions.OpenContext; +import org.apache.flink.api.common.state.MapState; +import org.apache.flink.api.common.state.MapStateDescriptor; +import org.apache.flink.api.common.state.StateTtlConfig; +import org.apache.flink.api.common.state.ValueState; +import org.apache.flink.api.common.state.ValueStateDescriptor; +import org.apache.flink.api.common.typeinfo.Types; +import org.apache.flink.api.java.functions.KeySelector; +import org.apache.flink.api.java.tuple.Tuple2; +import org.apache.flink.api.java.typeutils.ListTypeInfo; +import org.apache.flink.api.java.typeutils.TupleTypeInfo; +import org.apache.flink.metrics.Counter; +import org.apache.flink.streaming.api.functions.KeyedProcessFunction; +import org.apache.flink.table.data.GenericRowData; +import org.apache.flink.table.data.RowData; +import org.apache.flink.table.data.utils.JoinedRowData; +import org.apache.flink.table.runtime.dataview.PerKeyStateDataViewStore; +import org.apache.flink.table.runtime.generated.AggsHandleFunction; +import org.apache.flink.table.runtime.generated.GeneratedAggsHandleFunction; +import org.apache.flink.table.runtime.generated.GeneratedRecordComparator; +import org.apache.flink.table.runtime.generated.GeneratedRecordEqualiser; +import org.apache.flink.table.runtime.generated.RecordEqualiser; +import org.apache.flink.table.runtime.keyselector.RowDataKeySelector; +import org.apache.flink.table.runtime.typeutils.InternalTypeInfo; +import org.apache.flink.table.types.logical.BigIntType; +import org.apache.flink.table.types.logical.LogicalType; +import org.apache.flink.types.RowKind; +import org.apache.flink.util.Collector; + +import org.slf4j.Logger; +import org.slf4j.LoggerFactory; + +import java.io.IOException; +import java.util.ArrayList; +import java.util.Comparator; +import java.util.List; + +import static org.apache.flink.table.runtime.util.StateConfigUtil.createTtlConfig; + +/** + * The NonTimeRowsUnboundedPrecedingFunction class is a specialized implementation for processing + * unbounded OVER window aggregations, particularly for non-time-based rows queries in Apache Flink. + * It maintains strict ordering of rows within partitions and handles the full changelog lifecycle + * (inserts, updates, deletes). + * + * <p>Key Components and Assumptions + * + * <p>Data Structure Design: (1) Maintains a sorted list of tuples containing sort keys and lists of + * IDs for each key (2) Each incoming row is assigned a unique Long ID (starting from + * Long.MIN_VALUE) (3) Uses multiple state types to track rows, sort orders, and aggregations + * + * <p>State Management: (1) idState: Counter for generating unique row IDs (2) sortedListState: + * Ordered list of sort keys with their associated row IDs (3) valueMapState: Maps IDs to their + * corresponding input rows (4) accMapState: Maps sort keys to their accumulated values + * + * <p>Processing Model: (1) For inserts/updates: Adds rows to the appropriate position based on sort + * key (2) For deletes: Removes rows by matching both sort key and row content (3) Recalculates + * aggregates for affected rows and emits the appropriate events (4) Skips redundant events when + * accumulators haven't changed to reduce network traffic + * + * <p>Optimization Assumptions: (1) Skip emitting updates when accumulators haven't changed to + * reduce network traffic (2) Uses state TTL for automatic cleanup of stale data (3) Carefully + * manages row state to support incremental calculations + * + * <p>Retraction Handling: (1) Handles retraction mode (DELETE/UPDATE_BEFORE) events properly (2) + * Supports the proper processing of changelog streams + * + * <p>Limitations + * + * <p>Linear search performance: - The current implementation uses a linear search to find the + * correct position for each sort key. This can be optimized using a binary search for large state + * sizes. + * + * <p>State size and performance: - The implementation maintains multiple state types that could + * grow large with high cardinality data + * + * <p>Linear recalculation: - When processing updates, all subsequent elements need to be + * recalculated, which could be inefficient for large windows + */ +public class NonTimeRowsUnboundedPrecedingFunction<K> Review Comment: Introduced `AbstractNonTimeUnboundedPrecedingOver` -- 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: issues-unsubscr...@flink.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org
