Shulou(Shulou.com)05/31 Report--

The content of this article mainly focuses on how to understand the spark task scheduling system. The content of the article is clear and clear. It is very suitable for beginners to learn and is worth reading. Interested friends can follow the editor to read together. I hope you can get something through this article!

Spark's task scheduling system is as follows:

It can be seen from the above picture that DAG is generated by RDD Objects and then enters the DAGScheduler phase. DAGScheduler is a high-level scheduler for state. DAGScheduler splits DAG into many tasks, and each group of tasks is a state. Whenever it encounters shuffle, it will generate a new state. We can see that there are three state;DAGScheduler in the above picture that need to record the physical and chemical actions such as which RDD is stored on disk. At the same time, we need to find the optimal scheduling of task, such as data locality. DAGScheduler also monitors failures due to shuffle output, and if such a failure occurs, you may need to resubmit the state:

You can see that TaskScheduler is a trait. In the current spark system, the implementation class of TaskScheduler has only one TaskSchedulerImpl:

Take a look at the TaskSet source code:

From the first parameter tasks of the TaskSet source code, you can see that it is an array of Task, containing an array of Task.

Thank you for your reading. I believe you have a certain understanding of "how to understand the spark task scheduling system". Go and practice it. If you want to know more about it, you can follow the website! The editor will continue to bring you better articles!

Welcome to subscribe "Shulou Technology Information " to get latest news, interesting things and hot topics in the IT industry, and controls the hottest and latest Internet news, technology news and IT industry trends.