eagle-jpm/eagle-jpm-analyzer/src/main/java/org/apache/eagle/jpm/analyzer/mr/suggestion/MapReduceSplitSettingProcessor.java

/*
 * 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.eagle.jpm.analyzer.mr.suggestion;

import org.apache.eagle.jpm.analyzer.Processor;
import org.apache.eagle.jpm.analyzer.meta.model.MapReduceAnalyzerEntity;
import org.apache.eagle.jpm.analyzer.publisher.Result;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;

public class MapReduceSplitSettingProcessor implements Processor<MapReduceAnalyzerEntity> {

    private MapReduceJobSuggestionContext context;

    public MapReduceSplitSettingProcessor(MapReduceJobSuggestionContext context) {
        this.context = context;
    }

    @Override
    public Result.ProcessorResult process(MapReduceAnalyzerEntity jobAnalysisEntity) {
        StringBuilder sb = new StringBuilder();

        if (context.getJobconf().getLong(FileInputFormat.SPLIT_MINSIZE, 0) > 1) {
            sb.append("Best practice: don't set " + FileInputFormat.SPLIT_MINSIZE);
            sb.append(", because it may lower data locality, hence maps will run slower.\n");
            return new Result.ProcessorResult(Result.RuleType.SPLIT, Result.ResultLevel.INFO, sb.toString());
        }
        return null;
    }
}