[ 
https://issues.apache.org/jira/browse/FLINK-17493?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17107331#comment-17107331
 ] 

nobleyd commented on FLINK-17493:
---------------------------------

[~xintongsong], I readjusted the affected version, which was partially 
inaccurate. Here I give a picture below:

!image-2020-05-14-21-58-59-152.png|width=701,height=301!
 # Start a job called JobA, which read from kafka and sink to cassandra. The 
flink web-ui shows that there is totally 12302 direct memory buffers are used. 
It includes 12288 network segments, and is allocated at the start.
 # Stop the JobA, the direct memory buffers will decreased(maybe kafka use 
direct memory also), but not be 12288.
 # Restart the JobA, then you will find that the direct memory buffers used 
will be greater than 12302.
 # Repeat step2 and step3, the direct memory buffers used will be greater and 
greater, until it reached the MaxDirectMemorySize(decided by jvm options, which 
is framework-off-heap+task-off-heap+network-memory). 

> Possible direct memory leak in cassandra sink
> ---------------------------------------------
>
>                 Key: FLINK-17493
>                 URL: https://issues.apache.org/jira/browse/FLINK-17493
>             Project: Flink
>          Issue Type: Bug
>          Components: Connectors / Cassandra
>    Affects Versions: 1.9.0, 1.10.0
>            Reporter: nobleyd
>            Priority: Major
>         Attachments: image-2020-05-14-21-58-59-152.png
>
>
> # Cassandra Sink use direct memorys.
>  # Start a standalone cluster(1 machines) for test.
>  # After the cluster started, check the flink web-ui, and record the task 
> manager's memory info. I mean the direct memory part info.
>  # Start a job which read from kafka and write to cassandra using the 
> cassandra sink, and you can see that the direct memory count in 'Outside JVM' 
> part go up.
>  # Stop the job, and the direct memory count is not decreased(using 'jmap 
> -histo:live pid' to make the task manager gc).
>  # Repeat serveral times, the direct memory count will be more and more.



--
This message was sent by Atlassian Jira
(v8.3.4#803005)

Reply via email to