I haven't played with these settings myself so this is just speculation but if we think about this issue as normal cores and threads in a distributed system then in your cluster you can use up to 12 cores (4 * 3 machines) and 24 threads (8 * 3 machines). In your first two examples you are giving your job a fair number of cores (potential computation space) but the number of threads (jobs) to run on those cores is so limited that you aren't able to use much of the processing power allocated and thus the job is slower even though there is more computation resources allocated.

您提到您关心的是shuffle步骤—虽然在shuffle步骤中限制开销很好，但通常更重要的是利用集群的并行化。考虑一个极端的情况——一个没有shuffle的单线程程序。

I haven't played with these settings myself so this is just speculation but if we think about this issue as normal cores and threads in a distributed system then in your cluster you can use up to 12 cores (4 * 3 machines) and 24 threads (8 * 3 machines). In your first two examples you are giving your job a fair number of cores (potential computation space) but the number of threads (jobs) to run on those cores is so limited that you aren't able to use much of the processing power allocated and thus the job is slower even though there is more computation resources allocated.

您提到您关心的是shuffle步骤—虽然在shuffle步骤中限制开销很好，但通常更重要的是利用集群的并行化。考虑一个极端的情况——一个没有shuffle的单线程程序。

To hopefully make all of this a little more concrete, here’s a worked example of configuring a Spark app to use as much of the cluster as possible: Imagine a cluster with six nodes running NodeManagers, each equipped with 16 cores and 64GB of memory. The NodeManager capacities, yarn.nodemanager.resource.memory-mb and yarn.nodemanager.resource.cpu-vcores, should probably be set to 63 * 1024 = 64512 (megabytes) and 15 respectively. We avoid allocating 100% of the resources to YARN containers because the node needs some resources to run the OS and Hadoop daemons. In this case, we leave a gigabyte and a core for these system processes. Cloudera Manager helps by accounting for these and configuring these YARN properties automatically. The likely first impulse would be to use --num-executors 6 --executor-cores 15 --executor-memory 63G. However, this is the wrong approach because: 63GB + the executor memory overhead won’t fit within the 63GB capacity of the NodeManagers. The application master will take up a core on one of the nodes, meaning that there won’t be room for a 15-core executor on that node. 15 cores per executor can lead to bad HDFS I/O throughput. A better option would be to use --num-executors 17 --executor-cores 5 --executor-memory 19G. Why? This config results in three executors on all nodes except for the one with the AM, which will have two executors. --executor-memory was derived as (63/3 executors per node) = 21. 21 * 0.07 = 1.47. 21 – 1.47 ~ 19.

Cloudera博客的一篇文章给出了解释，How-to: tuning Your Apache Spark Jobs (Part 2)。

我认为其中一个主要原因是地方性。您的输入文件大小为165G，文件的相关块当然分布在多个datanode上，更多的执行器可以避免网络复制。

尝试设置executor num等于blocks count，我认为可以更快。

根据Sandy Ryza的说法，当你在HDFS上运行spark应用程序时

我注意到HDFS客户端有大量并发的问题 线程。粗略估计，每个执行者最多可以执行5个任务 实现全写吞吐量，所以最好保持数量 每个执行程序的内核数低于这个数字。

所以我相信你的第一个配置比第三个配置慢是因为HDFS的I/O吞吐量不好

在2.)配置中，您减少了并行任务，因此我认为您的比较是不公平的。 使——num-executors至少为5。 因此，与1.)配置中的21个任务相比，您将有20个任务正在运行。 这样比较对我来说就公平了。

另外，请相应地计算执行程序内存。