hadoop-hdfs-issues mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Daryn Sharp (JIRA)" <j...@apache.org>
Subject [jira] [Commented] (HDFS-6840) Clients are always sent to the same datanode when read is off rack
Date Tue, 09 Sep 2014 16:07:29 GMT

    [ https://issues.apache.org/jira/browse/HDFS-6840?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14127156#comment-14127156
] 

Daryn Sharp commented on HDFS-6840:
-----------------------------------

In addition to Jason's comment, I'm mildly concerned with the tests assuming and hardcoding
the ordering based on seed.  Presumably the jdk could change how the seeding works at anytime
which would cause test failures.  Note that a few months ago I saw a jdk bug about how java's
randomness isn't very random at all so it's possible the ordering could change in the near
future.

> 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
>
>
> 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