zhu.qing created FLINK-8526:
-------------------------------
Summary: When use some parallelism, the program will stuck in some setting.
Key: FLINK-8526
URL:
https://issues.apache.org/jira/browse/FLINK-8526 Project: Flink
Issue Type: Bug
Components: Cluster Management, Java API, Local Runtime
Affects Versions: 1.4.0
Environment: 8 machines(96GB and 24 cores) and 20 taskslot per taskmanager. twitter-2010 dataset. And parallelism setting to 80. I run my code in standalone mode.
Reporter: zhu.qing
Attachments: T2AdjActiveV.java, T2AdjMessage.java
The next program will stuck at some special parallelism in some situation. In the code attached. And I want to know the relation between parallelism and running task.When parallelism is 80. The program will always stuck. And when parallelism is 100. everything goes well. And I found when the parallelism equals to number of taskslots. The program is not fasted. And probably caused network buffer not enough. How networker buffer related to parallelism
--
This message was sent by Atlassian JIRA
(v7.6.3#76005)