hadoop-hdfs-issues mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Kihwal Lee (JIRA)" <j...@apache.org>
Subject [jira] [Commented] (HDFS-6221) Webhdfs should recover from dead DNs
Date Wed, 13 Jan 2016 19:16:40 GMT

    [ https://issues.apache.org/jira/browse/HDFS-6221?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15096830#comment-15096830
] 

Kihwal Lee commented on HDFS-6221:
----------------------------------

bq. We've repeatedly observed the jetty acceptor thread silently dying in the DNs
After converting DN to use netty, this is no longer a problem. jetty is still there, but only
handles infrequent non-webhdfs http requests.

> Webhdfs should recover from dead DNs
> ------------------------------------
>
>                 Key: HDFS-6221
>                 URL: https://issues.apache.org/jira/browse/HDFS-6221
>             Project: Hadoop HDFS
>          Issue Type: Bug
>          Components: datanode, webhdfs
>    Affects Versions: 2.0.0-alpha, 3.0.0
>            Reporter: Daryn Sharp
>            Assignee: Daryn Sharp
>
> We've repeatedly observed the jetty acceptor thread silently dying in the DNs.  The webhdfs
servlet may also "disappear" and jetty returns non-json 404s.
> One approach to make webhdfs more resilient to bad DNs is dfsclient-like fetching of
block locations to directly access the DNs instead of relying on a NN redirect that may repeatedly
send the client to the same faulty DN(s).



--
This message was sent by Atlassian JIRA
(v6.3.4#6332)

Mime
View raw message