hadoop-hdfs-issues mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Nathan Roberts (JIRA)" <j...@apache.org>
Subject [jira] [Commented] (HDFS-6166) revisit balancer so_timeout
Date Fri, 28 Mar 2014 22:18:17 GMT

    [ https://issues.apache.org/jira/browse/HDFS-6166?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13951493#comment-13951493
] 

Nathan Roberts commented on HDFS-6166:
--------------------------------------

Maybe our two comments passed in the mail. Yes I tested internally. It's been running on a
400 node cluster for 1 day. I ran with bandwidths of 500K, 6MB, 20MB. With 500K there were
timeouts, but no thread quota exceeded failures.

> revisit balancer so_timeout 
> ----------------------------
>
>                 Key: HDFS-6166
>                 URL: https://issues.apache.org/jira/browse/HDFS-6166
>             Project: Hadoop HDFS
>          Issue Type: Bug
>          Components: balancer
>    Affects Versions: 3.0.0, 2.3.0
>            Reporter: Nathan Roberts
>            Assignee: Nathan Roberts
>            Priority: Blocker
>         Attachments: HDFS-6166.patch
>
>
> HDFS-5806 changed the socket read timeout for the balancer connection to DN to 60 seconds.
This works as long as balancer bandwidth is such that it's safe to assume that the DN will
easily complete the operation within this time. Obviously this isn't a good assumption. When
this assumption isn't valid, the balancer will timeout the cmd BUT it will then be out-of-sync
with the datanode (balancer thinks the DN has room to do more work, DN is still working on
the request and will fail any subsequent requests with "threads quota exceeded errors"). This
causes expensive NN traffic via getBlocks() and also causes lots of WARNS int the balancer
log.
> Unfortunately the protocol is such that it's impossible to tell if the DN is busy working
on replacing the block, OR is in bad shape and will never finish.
> So, in the interest of a small change to deal with both situations, I propose the following
two changes:
> * Crank of the socket read timeout to 20 minutes
> * Delay looking at a node for a bit if we did timeout in this way (the DN could still
have xceiver threads working on the replace 



--
This message was sent by Atlassian JIRA
(v6.2#6252)

Mime
View raw message