pvary commented on code in PR #15996: URL: https://github.com/apache/iceberg/pull/15996#discussion_r3094473615
########## flink/v2.1/flink/src/main/java/org/apache/iceberg/flink/maintenance/operator/EqualityConvertWorker.java: ########## @@ -0,0 +1,219 @@ +/* + * 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.iceberg.flink.maintenance.operator; + +import java.io.Serializable; +import java.util.List; +import java.util.Objects; +import org.apache.flink.annotation.Internal; +import org.apache.flink.api.common.functions.OpenContext; +import org.apache.flink.api.common.state.ListState; +import org.apache.flink.api.common.state.ListStateDescriptor; +import org.apache.flink.api.common.state.ValueState; +import org.apache.flink.api.common.state.ValueStateDescriptor; +import org.apache.flink.api.common.typeinfo.TypeInformation; +import org.apache.flink.api.common.typeinfo.Types; +import org.apache.flink.metrics.Counter; +import org.apache.flink.streaming.api.functions.KeyedProcessFunction; +import org.apache.flink.util.Collector; +import org.apache.iceberg.relocated.com.google.common.collect.Lists; +import org.slf4j.Logger; +import org.slf4j.LoggerFactory; + +/** + * Parallel worker that maintains a shard of the primary key index. Keyed by the full serialized + * primary key ({@link SerializedEqualityValues}), each instance handles a subset of PK values. + * + * <p>Uses phase-aware buffering to guarantee ordering with parallel readers. ADD_DATA_ROW commands + * are processed immediately until a RESOLVE_DELETE arrives. At that point, subsequent commands are + * buffered and processed on event-time timers, which fire only after watermarks confirm all + * prior-phase records have been received from all readers. + * + * <p>Detects main branch changes via {@link IndexCommand#mainSnapshotId()} and clears stale index + * entries when the main snapshot changes. + */ +@Internal +public class EqualityConvertWorker + extends KeyedProcessFunction<SerializedEqualityValues, IndexCommand, DVPosition> { + + private static final Logger LOG = LoggerFactory.getLogger(EqualityConvertWorker.class); + + private static final String RESOLVED_DELETE_NUM_METRIC = "resolvedDeleteNum"; + private static final String INDEXED_KEY_NUM_METRIC = "indexedKeyNum"; + + private transient ValueState<Long> mainSnapshotVersion; + private transient ListState<DVPosition> dataRowPositions; + private transient ListState<TimestampedCommand> pendingCommands; Review Comment: Executing multiple conversions add serious complexity. Does this worth it? Shall we just do it one-by-one? We probably also would like to keep the original change sequence in the main branch too. That means committing changes one-by-one -- 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]
