hadoop-hdfs-issues mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Aaron T. Myers (JIRA)" <j...@apache.org>
Subject [jira] [Commented] (HDFS-6840) Clients are always sent to the same datanode when read is off rack
Date Thu, 18 Sep 2014 22:48:34 GMT

    [ https://issues.apache.org/jira/browse/HDFS-6840?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14139643#comment-14139643
] 

Aaron T. Myers commented on HDFS-6840:
--------------------------------------

Latest patch looks good to me, +1. I agree that we can reasonably move the improvements to
the tests to make them deterministic to another JIRA. Andrew, could you please go ahead and
file that?

> Clients are always sent to the same datanode when read is off rack
> ------------------------------------------------------------------
>
>                 Key: HDFS-6840
>                 URL: https://issues.apache.org/jira/browse/HDFS-6840
>             Project: Hadoop HDFS
>          Issue Type: Bug
>    Affects Versions: 2.5.0
>            Reporter: Jason Lowe
>            Assignee: Andrew Wang
>            Priority: Critical
>         Attachments: hdfs-6840.001.patch, hdfs-6840.002.patch, hdfs-6840.003.patch
>
>
> After HDFS-6268 the sorting order of block locations is deterministic for a given block
and locality level (e.g.: local, rack. off-rack), so off-rack clients all see the same datanode
for the same block.  This leads to very poor behavior in distributed cache localization and
other scenarios where many clients all want the same block data at approximately the same
time.  The one datanode is crushed by the load while the other replicas only handle local
and rack-local requests.



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

Mime
View raw message