(K.hashcode & Integer.MAX_VALE) % (reducer number)
hashpartitioner 相同key的数据一定会在同一个reducer中，但一个reducer中不就只有一个key
class HostPartitioner(ins:Array[String]) extends Partitioner {
val parMap = new mutable.HashMap[String, Int]()
val count = 0
for (i <- ins) {
parMap += (i -> count)
count += 1
}
override def numPartitions:Int = ins.length
verride def getPartition(key: Any):Int = {
parMap.getOrElse(key.toString, 0)
}
}
调用的时候
val hostPartitioner = new HostPartitioner()
rdd.partitionBy(hostPartitioner)
rdd.partitionBy(new HashPartitioner(6))