[
https://issues.apache.org/jira/browse/HDFS-7597?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14279042#comment-14279042
]
Daryn Sharp commented on HDFS-7597:
-----------------------------------
I meant to say the map that the builder actually creates. The code for get/put
is substantially more complicated than {{LRUMap}} so it can provide features we
don't need in this use case.
Maybe a CHM would be faster. I went with a simple solution to resolve
recurring production issues. I'll try to run some quick benchmarks.
The test failure is due to the way the test is written. I need to update it.
> Clients seeking over webhdfs may crash the NN
> ---------------------------------------------
>
> Key: HDFS-7597
> URL: https://issues.apache.org/jira/browse/HDFS-7597
> Project: Hadoop HDFS
> Issue Type: Improvement
> Components: webhdfs
> Affects Versions: 2.0.0-alpha
> Reporter: Daryn Sharp
> Assignee: Daryn Sharp
> Priority: Critical
> Attachments: HDFS-7597.patch
>
>
> Webhdfs seeks involve closing the current connection, and reissuing a new
> open request with the new offset. The RPC layer caches connections so the DN
> keeps a lingering connection open to the NN. Connection caching is in part
> based on UGI. Although the client used the same token for the new offset
> request, the UGI is different which forces the DN to open another unnecessary
> connection to the NN.
> A job that performs many seeks will easily crash the NN due to fd exhaustion.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
