[
https://issues.apache.org/jira/browse/HDFS-7276?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14194803#comment-14194803
]
Colin Patrick McCabe commented on HDFS-7276:
--------------------------------------------
Re: deadlock discussion.
It's correct that the code would deadlock without {{notifyAll}} in its current
form. However, a simple fix would prevent this: the releasing code could
simply call {{notify}} whenever count < limit, instead of only calling it when
count == limit. This would prevent the "thundering herd" problem that the code
currently has. See http://en.wikipedia.org/wiki/Thundering_herd_problem. I
filed HDFS-7325 as a follow-up to fix this.
> Limit the number of byte arrays used by DFSOutputStream
> -------------------------------------------------------
>
> Key: HDFS-7276
> URL: https://issues.apache.org/jira/browse/HDFS-7276
> Project: Hadoop HDFS
> Issue Type: Improvement
> Components: hdfs-client
> Reporter: Tsz Wo Nicholas Sze
> Assignee: Tsz Wo Nicholas Sze
> Fix For: 2.6.0
>
> Attachments: h7276_20141021.patch, h7276_20141022.patch,
> h7276_20141023.patch, h7276_20141024.patch, h7276_20141027.patch,
> h7276_20141027b.patch, h7276_20141028.patch, h7276_20141029.patch,
> h7276_20141029b.patch, h7276_20141030.patch, h7276_20141031.patch
>
>
> When there are a lot of DFSOutputStream's writing concurrently, the number of
> outstanding packets could be large. The byte arrays created by those packets
> could occupy a lot of memory.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
