scala - Spark : coalesce very slow even the output data is very small

Question

我在 Spark 中有以下代码:

myData.filter(t => t.getMyEnum() == null)
      .map(t => t.toString)
      .saveAsTextFile("myOutput")

myOutput文件夹中有2000+个文件，但是t.getMyEnum() == null只有几个，所以输出记录很少。由于我不想只搜索 2000 多个输出文件中的几个输出，我尝试使用 coalesce 组合输出，如下所示:

myData.filter(t => t.getMyEnum() == null)
      .map(t => t.toString)
      .coalesce(1, false)
      .saveAsTextFile("myOutput")

然后工作变得非常慢!我想知道为什么它这么慢？只有少数输出记录分散在 2000 多个分区中？有没有更好的方法来解决这个问题？

Answer 1

if you're doing a drastic coalesce, e.g. to numPartitions = 1, this may result in your computation taking place on fewer nodes than you like (e.g. one node in the case of numPartitions = 1). To avoid this, you can pass shuffle = true. This will add a shuffle step, but means the current upstream partitions will be executed in parallel (per whatever the current partitioning is).

Note: With shuffle = true, you can actually coalesce to a larger number of partitions. This is useful if you have a small number of partitions, say 100, potentially with a few partitions being abnormally large. Calling coalesce(1000, shuffle = true) will result in 1000 partitions with the data distributed using a hash partitioner.

因此，尝试将 true 传递给 coalesce功能。 IE。

myData.filter(_.getMyEnum == null)
      .map(_.toString)
      .coalesce(1, shuffle = true)
      .saveAsTextFile("myOutput")