hadoop-hdfs-issues mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Anthony Hsu (JIRA)" <j...@apache.org>
Subject [jira] [Commented] (HDFS-6599) 2.4 addBlock is 10 to 20 times slower compared to 0.23
Date Fri, 20 Mar 2015 18:19:39 GMT

    [ https://issues.apache.org/jira/browse/HDFS-6599?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14371782#comment-14371782
] 

Anthony Hsu commented on HDFS-6599:
-----------------------------------

Thanks for the pointers, Kihwal.  We'll take a look at some of those patches and consider
applying them.

BTW, we applied the patch for this ticket and noticed a significant improvement in NameNode
latency and throughput!

> 2.4 addBlock is 10 to 20 times slower compared to 0.23
> ------------------------------------------------------
>
>                 Key: HDFS-6599
>                 URL: https://issues.apache.org/jira/browse/HDFS-6599
>             Project: Hadoop HDFS
>          Issue Type: Bug
>    Affects Versions: 2.3.0, 2.4.0
>            Reporter: Kihwal Lee
>            Assignee: Daryn Sharp
>            Priority: Blocker
>             Fix For: 2.5.0
>
>         Attachments: HDFS-6599.patch
>
>
> From one of our busiest 0.23 clusters:
> {panel}
> "AddBlockAvgTime" : 0.9514711501719515
> "CreateAvgTime" : 1.7564162389174
> "CompleteAvgTime" : 1.3310406035056548
> "BlockReceivedAndDeletedAvgTime" : 0.661210005151392
> {panel}
> From a not-so-busy 2.4 cluster:
> {panel}
> "AddBlockAvgTime" : 10.083333333333334
> "CreateAvgTime" : 1.0
> "CompleteAvgTime" : 1.1111111111111112
> "BlockReceivedAndDeletedAvgTime" : 0.07692307692307694
> {panel}
> When the 2.4 cluster gets a moderate amount of write requests, the latency is terrible.
E.g. addBlock goes upward of 60ms. 



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

Mime
View raw message