[
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-unsubscr...@hadoop.apache.org
For additional commands, e-mail: hdfs-issues-h...@hadoop.apache.org
