flink-issues mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "zhijiang (JIRA)" <j...@apache.org>
Subject [jira] [Commented] (FLINK-4545) Flink automatically manages TM network buffer
Date Sat, 18 Mar 2017 15:26:42 GMT

    [ https://issues.apache.org/jira/browse/FLINK-4545?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15931247#comment-15931247
] 

zhijiang commented on FLINK-4545:
---------------------------------

[~StephanEwen], thank you for so rich information! 
I agree with the above points and know well the considerations and future plans!
The current constant global buffer amount is replaced by the flexible minimum and maximum
range, which is especially helpful for current batch jobs and future better recovery for streaming.
Wish to see the changes quickly and participate in related parts!

> Flink automatically manages TM network buffer
> ---------------------------------------------
>
>                 Key: FLINK-4545
>                 URL: https://issues.apache.org/jira/browse/FLINK-4545
>             Project: Flink
>          Issue Type: Wish
>          Components: Network
>            Reporter: Zhenzhong Xu
>
> Currently, the number of network buffer per task manager is preconfigured and the memory
is pre-allocated through taskmanager.network.numberOfBuffers config. In a Job DAG with shuffle
phase, this number can go up very high depends on the TM cluster size. The formula for calculating
the buffer count is documented here (https://ci.apache.org/projects/flink/flink-docs-master/setup/config.html#configuring-the-network-buffers).
 
> #slots-per-TM^2 * #TMs * 4
> In a standalone deployment, we may need to control the task manager cluster size dynamically
and then leverage the up-coming Flink feature to support scaling job parallelism/rescaling
at runtime. 
> If the buffer count config is static at runtime and cannot be changed without restarting
task manager process, this may add latency and complexity for scaling process. I am wondering
if there is already any discussion around whether the network buffer should be automatically
managed by Flink or at least expose some API to allow it to be reconfigured. Let me know if
there is any existing JIRA that I should follow.



--
This message was sent by Atlassian JIRA
(v6.3.15#6346)

Mime
View raw message