[
https://issues.apache.org/jira/browse/FLINK-2853?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14964471#comment-14964471
]
ASF GitHub Bot commented on FLINK-2853:
---------------------------------------
Github user gallenvara commented on a diff in the pull request:
https://github.com/apache/flink/pull/1267#discussion_r42453815
--- Diff:
flink-benchmark/src/test/java/org/apache/flink/benchmark/runtime/operates/hash/MutableHashTablePerformanceBenchmark.java
---
@@ -0,0 +1,361 @@
+/**
+ * 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
+ * <p/>
+ * http://www.apache.org/licenses/LICENSE-2.0
+ * <p/>
+ * 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.benchmark.runtime.operates.hash;
+
+import java.io.IOException;
+import java.util.List;
+import java.util.concurrent.TimeUnit;
+
+import org.apache.flink.api.common.typeutils.TypeComparator;
+import org.apache.flink.api.common.typeutils.TypePairComparator;
+import org.apache.flink.api.common.typeutils.TypeSerializer;
+import org.apache.flink.core.memory.MemorySegment;
+import org.apache.flink.runtime.io.disk.iomanager.IOManager;
+import org.apache.flink.runtime.io.disk.iomanager.IOManagerAsync;
+import org.apache.flink.runtime.jobgraph.tasks.AbstractInvokable;
+import org.apache.flink.runtime.memory.MemoryAllocationException;
+import org.apache.flink.runtime.memory.MemoryManager;
+import org.apache.flink.runtime.operators.hash.MutableHashTable;
+import org.apache.flink.runtime.operators.testutils.DummyInvokable;
+import org.apache.flink.runtime.operators.testutils.types.StringPair;
+import
org.apache.flink.runtime.operators.testutils.types.StringPairComparator;
+import
org.apache.flink.runtime.operators.testutils.types.StringPairPairComparator;
+import
org.apache.flink.runtime.operators.testutils.types.StringPairSerializer;
+import org.apache.flink.util.MutableObjectIterator;
+
+import org.junit.Assert;
+import org.openjdk.jmh.annotations.*;
+import org.openjdk.jmh.runner.Runner;
+import org.openjdk.jmh.runner.options.Options;
+import org.openjdk.jmh.runner.options.OptionsBuilder;
+
+import static org.junit.Assert.fail;
+
+@State(Scope.Thread)
+@BenchmarkMode(Mode.AverageTime)
+@OutputTimeUnit(TimeUnit.MILLISECONDS)
+public class MutableHashTablePerformanceBenchmark {
+
+ private static final AbstractInvokable MEM_OWNER = new DummyInvokable();
+
+ private MemoryManager memManager;
+ private IOManager ioManager;
+
+ private TypeSerializer<StringPair> pairBuildSideAccesssor;
+ private TypeSerializer<StringPair> pairProbeSideAccesssor;
+ private TypeComparator<StringPair> pairBuildSideComparator;
+ private TypeComparator<StringPair> pairProbeSideComparator;
+ private TypePairComparator<StringPair, StringPair> pairComparator;
+
+ private static final String COMMENT = "this comments should contains a
96 byte data, 100 plus another integer value and seperator char.";
+
+
+ @Setup
+ public void setup() {
+ this.pairBuildSideAccesssor = new StringPairSerializer();
+ this.pairProbeSideAccesssor = new StringPairSerializer();
+ this.pairBuildSideComparator = new StringPairComparator();
+ this.pairProbeSideComparator = new StringPairComparator();
+ this.pairComparator = new StringPairPairComparator();
+
+ this.memManager = new MemoryManager(64 * 1024 * 1024, 1);
+ this.ioManager = new IOManagerAsync();
+ }
+
+ @TearDown
+ public void tearDown() {
+ // shut down I/O manager and Memory Manager and verify the
correct shutdown
+ this.ioManager.shutdown();
+ if (!this.ioManager.isProperlyShutDown()) {
+ fail("I/O manager was not property shut down.");
+ }
+ if (!this.memManager.verifyEmpty()) {
+ fail("Not all memory was properly released to the
memory manager --> Memory Leak.");
+ }
+ }
+
+ @Benchmark
+ public void compareMutableHashTableWithBloomFilter1() throws
IOException {
+ // ----------------------------------------------90% filtered
during probe spill phase-----------------------------------------
+ // create a build input with 1000000 records with key spread
between [0 -- 10000000] with step of 10 for nearby records.
+ int buildSize = 1000000;
+ int buildStep = 10;
+ int buildScope = buildStep * buildSize;
+ // create a probe input with 5000000 records with key spread
between [0 -- 1000000] with distance of 1 for nearby records.
+ int probeSize = 5000000;
+ int probeStep = 1;
+ int probeScope = buildSize;
+
+ int expectedResult = 500000;
+
+ this.hybridHashJoin(buildSize, buildStep, buildScope,
probeSize, probeStep, probeScope, expectedResult, true);
+
+ System.out.println("HybridHashJoin2:");
--- End diff --
Yes,that's right.I have submitted a new PR for correcting these problems.
> Apply JMH on MutableHashTablePerformanceBenchmark class.
> --------------------------------------------------------
>
> Key: FLINK-2853
> URL: https://issues.apache.org/jira/browse/FLINK-2853
> Project: Flink
> Issue Type: Sub-task
> Components: Tests
> Reporter: GaoLun
> Assignee: GaoLun
> Priority: Minor
> Labels: easyfix
>
> JMH is a Java harness for building, running, and analysing
> nano/micro/milli/macro benchmarks.Use JMH to replace the old micro benchmarks
> method in order to get much more accurate results.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
