Myasuka commented on a change in pull request #19177: URL: https://github.com/apache/flink/pull/19177#discussion_r839261530
########## File path: flink-state-backends/flink-statebackend-rocksdb/src/test/java/org/apache/flink/contrib/streaming/state/benchmark/RescalingBenchmark.java ########## @@ -0,0 +1,225 @@ +/* + * 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.contrib.streaming.state.benchmark; + +import org.apache.flink.api.common.state.ValueState; +import org.apache.flink.api.common.state.ValueStateDescriptor; +import org.apache.flink.api.java.functions.KeySelector; +import org.apache.flink.configuration.Configuration; +import org.apache.flink.runtime.checkpoint.OperatorSubtaskState; +import org.apache.flink.runtime.operators.testutils.MockEnvironment; +import org.apache.flink.runtime.operators.testutils.MockEnvironmentBuilder; +import org.apache.flink.runtime.operators.testutils.MockInputSplitProvider; +import org.apache.flink.runtime.state.CheckpointStorageAccess; +import org.apache.flink.runtime.state.KeyGroupRangeAssignment; +import org.apache.flink.runtime.state.StateBackend; +import org.apache.flink.streaming.api.functions.KeyedProcessFunction; +import org.apache.flink.streaming.api.operators.KeyedProcessOperator; +import org.apache.flink.streaming.runtime.streamrecord.StreamRecord; +import org.apache.flink.streaming.util.AbstractStreamOperatorTestHarness; +import org.apache.flink.streaming.util.KeyedOneInputStreamOperatorTestHarness; +import org.apache.flink.util.Collector; + +import java.io.IOException; +import java.util.Arrays; +import java.util.Random; + +import static org.apache.flink.api.common.typeinfo.PrimitiveArrayTypeInfo.BYTE_PRIMITIVE_ARRAY_TYPE_INFO; + +/** The benchmark of rescaling from savepoint. */ +public class RescalingBenchmark { + // numberOfKeys, keyLen and valueLen are used to control the size of state. + private final int numberOfKeys; + private final int keyLen; + private final int valueLen; + private final int maxParallelism; + + private final int parallelismBefore; + private final int parallelismAfter; + + private final boolean isSafeToReuseState; + private final Random random = new Random(0); + + private final StateBackend stateBackend; + private final CheckpointStorageAccess checkpointStorageAccess; + + private OperatorSubtaskState stateForRescaling; + private OperatorSubtaskState stateForSubtask; + private KeyedOneInputStreamOperatorTestHarness subtaskHarness; + + public RescalingBenchmark( + final int numberOfKeys, + final int kenLen, + final int valueLen, + final int parallelismBefore, + final int parallelismAfter, + final int maxParallelism, + final boolean isSafeToReuseState, Review comment: After rethink of how `RescalingBenchmark` should work, I think we should leave how keys are generated for user who call this benchmark. Moreover, we should also let the `KeyedProcessFunction` which used to update state open for users. In other word, the `stateProcessFunction` should also be a parameter. Last but not least, since current `RescalingBenchmark` has too many parameters in constructor, we should better to use `RescalingBenchmarkBuilder` here. -- 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
