Mailing-List: contact hdfs-issues-help@hadoop.apache.org; run by ezmlm
Precedence: bulk
Reply-To: hdfs-issues@hadoop.apache.org
Date: Sat, 15 Dec 2012 01:28:13 +0000 (UTC)
From: "Colin Patrick McCabe (JIRA)" <jira@apache.org>
To: hdfs-issues@hadoop.apache.org
Message-ID: <JIRA.12618381.1354310785836.10090.1355534893658@arcas>
In-Reply-To: <JIRA.12618381.1354310785836@arcas>
References: <JIRA.12618381.1354310785836@arcas>
Subject: [jira] [Commented] (HDFS-4253) block replica reads get hot-spots
 due to NetworkTopology#pseudoSortByDistance
MIME-Version: 1.0
Content-Type: text/plain; charset=utf-8
Content-Transfer-Encoding: 7bit


    [ https://issues.apache.org/jira/browse/HDFS-4253?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13532864#comment-13532864 ] 

Colin Patrick McCabe commented on HDFS-4253:
--------------------------------------------

Thanks for clarifying that.  I still think there's a problem, though-- I don't see any reason why shuffle(a) could not be equal to shuffle(b), for two completely unrelated DatanodeIDs a and b.  This could be fixed by checking something that's supposed to be unique in the case where the two agree-- like the name field.  It also seems better to just use {{hashCode}}, rather than creating your own random set of random ints associated with objects.
                
> block replica reads get hot-spots due to NetworkTopology#pseudoSortByDistance
> -----------------------------------------------------------------------------
>
>                 Key: HDFS-4253
>                 URL: https://issues.apache.org/jira/browse/HDFS-4253
>             Project: Hadoop HDFS
>          Issue Type: Bug
>    Affects Versions: 3.0.0, 2.0.2-alpha
>            Reporter: Andy Isaacson
>            Assignee: Andy Isaacson
>         Attachments: hdfs4253-1.txt, hdfs4253-2.txt, hdfs4253.txt
>
>
> When many nodes (10) read from the same block simultaneously, we get asymmetric distribution of read load.  This can result in slow block reads when one replica is serving most of the readers and the other replicas are idle.  The busy DN bottlenecks on its network link.
> This is especially visible with large block sizes and high replica counts (I reproduced the problem with {{-Ddfs.block.size=4294967296}} and replication 5), but the same behavior happens on a small scale with normal-sized blocks and replication=3.
> The root of the problem is in {{NetworkTopology#pseudoSortByDistance}} which explicitly does not try to spread traffic among replicas in a given rack -- it only randomizes usage for off-rack replicas.

--
This message is automatically generated by JIRA.
If you think it was sent incorrectly, please contact your JIRA administrators
For more information on JIRA, see: http://www.atlassian.com/software/jira