/**
* Choose a partitioner to use for a cogroup-like operation between a number of RDDs.
*
* If any of the RDDs already has a partitioner, choose that one.
*
* Otherwise, we use a default HashPartitioner. For the number of partitions, if
* spark.default.parallelism is set, then we'll use the value from SparkContext
* defaultParallelism, otherwise we'll use the max number of upstream partitions.
*
* Unless spark.default.parallelism is set, the number of partitions will be the
* same as the number of partitions in the largest upstream RDD, as this should
* be least likely to cause out-of-memory errors.
*
* We use two method parameters (rdd, others) to enforce callers passing at least 1 RDD.
*/
def defaultPartitioner(rdd: RDD[_], others: RDD[_]*): Partitioner = {
val bySize = (Seq(rdd) ++ others).sortBy(_.partitions.length).reverse
for (r <- bySize if r.partitioner.isDefined && r.partitioner.get.numPartitions > 0) {
return r.partitioner.get
}
if (rdd.context.conf.contains("spark.default.parallelism")) {
new HashPartitioner(rdd.context.defaultParallelism)
} else {
new HashPartitioner(bySize.head.partitions.length)
}
}
}
Spark Default Partitioner
最新推荐文章于 2023-11-04 23:59:59 发布