You are viewing a plain text version of this content. The canonical link for it is here.

Posted to hdfs-issues@hadoop.apache.org by "shuaiqi.guo (Jira)" <ji...@apache.org> on 2024/12/02 07:16:00 UTC

[jira] [Commented] (HDFS-17677) Too many DataStreamer and ResponseProcessor threads on client

    [ https://issues.apache.org/jira/browse/HDFS-17677?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17902178#comment-17902178 ] 

shuaiqi.guo commented on HDFS-17677:
------------------------------------

[~zhanghaobo] Hi, farmmamba. Thanks for your comment, and what I have reported is not an Exception, it's a performance issue. For examples, if there are 1000 hdfs files being written on the client for a long time, then 1000 DataStreamer threads and 1000 ResponseProcessor threads run on the client, it's inefficient and unnecessary.

> Too many DataStreamer and ResponseProcessor threads on client
> -------------------------------------------------------------
>
>                 Key: HDFS-17677
>                 URL: https://issues.apache.org/jira/browse/HDFS-17677
>             Project: Hadoop HDFS
>          Issue Type: Bug
>          Components: hdfs-client
>            Reporter: shuaiqi.guo
>            Priority: Major
>
>     hdfs client writes a large number of files at the same tine, then there are too many DataStreamer and ResponseProcessor threads on the client.
>     Is there any way to improve this situation? For example, using NIO based on epoll.



--
This message was sent by Atlassian Jira
(v8.20.10#820010)

---------------------------------------------------------------------
To unsubscribe, e-mail: hdfs-issues-unsubscribe@hadoop.apache.org
For additional commands, e-mail: hdfs-issues-help@hadoop.apache.org