hadoop PopularTagsIterator 源码

  • 2022-10-20
  • 浏览 (247)

haddop PopularTagsIterator 代码

文件路径:/hadoop-yarn-project/hadoop-yarn/hadoop-yarn-server/hadoop-yarn-server-resourcemanager/src/main/java/org/apache/hadoop/yarn/server/resourcemanager/scheduler/constraint/algorithm/iterators/PopularTagsIterator.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
 * <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.hadoop.yarn.server.resourcemanager.scheduler.constraint.algorithm.iterators;

import java.util.ArrayList;
import java.util.Collection;
import java.util.Collections;
import java.util.Iterator;
import java.util.List;
import java.util.NoSuchElementException;

import org.apache.hadoop.yarn.api.records.SchedulingRequest;

/**
 * Traverse Scheduling requests with the most popular tags (count) first.
 * Currently the count is per Batch but could use TagManager for global count.
 */
public class PopularTagsIterator implements Iterator<SchedulingRequest> {

  private final List<SchedulingRequest> schedulingRequestList;
  private int cursor;

  public PopularTagsIterator(Collection<SchedulingRequest> schedulingRequests) {
    this.schedulingRequestList = new ArrayList<>(schedulingRequests);
    // Most popular First
    Collections.sort(schedulingRequestList,
        (o1, o2) -> (int) getTagPopularity(o2) - (int) getTagPopularity(o1));

    this.cursor = 0;
  }

  private long getTagPopularity(SchedulingRequest o1) {
    long max = 0;
    for (String tag : o1.getAllocationTags()) {
      long count = schedulingRequestList.stream()
          .filter(req -> req.getAllocationTags().contains(tag)).count();
      if (count > max) {
        max = count;
      }
    }
    return max;
  }

  @Override
  public boolean hasNext() {
    return (cursor < schedulingRequestList.size());
  }

  @Override
  public SchedulingRequest next() {
    if (hasNext()) {
      return schedulingRequestList.get(cursor++);
    }
    throw new NoSuchElementException();
  }
}

相关信息

hadoop 源码目录

相关文章

hadoop SerialIterator 源码

hadoop package-info 源码

0  赞