yarn/src/main/scala/org/apache/spark/scheduler/cluster/YarnScheduler.scala


1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39

/*
 * 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.spark.scheduler.cluster

import org.apache.hadoop.yarn.util.RackResolver
import org.apache.log4j.{Level, Logger}

import org.apache.spark._
import org.apache.spark.scheduler.TaskSchedulerImpl
import org.apache.spark.util.Utils

private[spark] class YarnScheduler(sc: SparkContext) extends TaskSchedulerImpl(sc) {

  // RackResolver logs an INFO message whenever it resolves a rack, which is way too often.
  if (Logger.getLogger(classOf[RackResolver]).getLevel == null) {
    Logger.getLogger(classOf[RackResolver]).setLevel(Level.WARN)
  }

  // By default, rack is unknown
  override def getRackForHost(hostPort: String): Option[String] = {
    val host = Utils.parseHostPort(hostPort)._1
    Option(RackResolver.resolve(sc.hadoopConfiguration, host).getNetworkLocation)
  }
}