spark-reviews mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From JoshRosen <...@git.apache.org>
Subject [GitHub] spark pull request: [SPARK-9852] Let reduce tasks fetch multiple m...
Date Mon, 21 Sep 2015 21:16:32 GMT
Github user JoshRosen commented on a diff in the pull request:

    https://github.com/apache/spark/pull/8844#discussion_r40027112
  
    --- Diff: core/src/test/scala/org/apache/spark/scheduler/CustomShuffledRDD.scala ---
    @@ -0,0 +1,111 @@
    +/*
    + * 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
    +
    +import java.util.Arrays
    +
    +import org.apache.spark._
    +import org.apache.spark.rdd.RDD
    +
    +/**
    + * A Partitioner that might group together one or more partitions from the parent.
    + *
    + * @param parent a parent partitioner
    + * @param partitionStartIndices indices of partitions in parent that should create new
partitions
    + *   in child (this should be an array of increasing partition IDs). For example, if
we have a
    + *   parent with 5 partitions, and partitionStartIndices is [0, 2, 4], we get three output
    + *   partitions, corresponding to partition ranges [0, 1], [2, 3] and [4] of the parent
partitioner.
    + */
    +class CoalescedPartitioner(val parent: Partitioner, val partitionStartIndices: Array[Int])
    +  extends Partitioner {
    +
    +  @transient private lazy val parentPartitionMapping: Array[Int] = {
    +    val n = parent.numPartitions
    +    val result = new Array[Int](n)
    +    for (i <- 0 until partitionStartIndices.length) {
    +      val start = partitionStartIndices(i)
    +      val end = if (i < partitionStartIndices.length - 1) partitionStartIndices(i
+ 1) else n
    +      for (j <- start until end) {
    +        result(j) = i
    +      }
    +    }
    +    result
    +  }
    +
    +  override def numPartitions: Int = partitionStartIndices.size
    +
    +  override def getPartition(key: Any): Int = {
    +    parentPartitionMapping(parent.getPartition(key))
    +  }
    +
    +  override def equals(other: Any): Boolean = other match {
    +    case c: CoalescedPartitioner =>
    +      c.parent == parent && Arrays.equals(c.partitionStartIndices, partitionStartIndices)
    +    case _ =>
    +      false
    +  }
    +}
    +
    +private[spark] class CustomShuffledRDDPartition(
    +    val index: Int, val startIndexInParent: Int, val endIndexInParent: Int)
    +  extends Partition {
    +
    +  override def hashCode(): Int = index
    +}
    +
    +/**
    + * A special ShuffledRDD that supports a ShuffleDependency object from outside and launching
reduce
    + * tasks that read multiple map output partitions.
    + */
    +class CustomShuffledRDD[K, V, C](
    --- End diff --
    
    Same comment here: should this be `private[spark]`


---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at infrastructure@apache.org or file a JIRA ticket
with INFRA.
---

---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org


Mime
View raw message