[
https://issues.apache.org/jira/browse/HDFS-3513?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13423227#comment-13423227
]
Daryn Sharp commented on HDFS-3513:
-----------------------------------
Yes, {{HttpURLConnection}} on the client side will assume keep-alive (since
that's default behavior for http/1.1) but I've seen namenode servlets always
sending "Connection: close" in the response.
If the server is disabling keep-alive then every request creates a new socket
and a new ugi and a new filesystem, hence why the ugi caching would show such
an improvement. If however a keep-alive connection is used, I would _expect_
the same ugi to be used for all the pipelined requests. However, maybe each
request on a keep-alive gets a new ugi anyway...
> HttpFS should cache filesystems
> -------------------------------
>
> Key: HDFS-3513
> URL: https://issues.apache.org/jira/browse/HDFS-3513
> Project: Hadoop HDFS
> Issue Type: Improvement
> Affects Versions: 2.0.0-alpha
> Reporter: Alejandro Abdelnur
> Assignee: Alejandro Abdelnur
> Attachments: HDFS-3513.patch, HDFS-3513.patch, HDFS-3513.patch,
> HDFS-3513.patch
>
>
> HttpFS opens and closes a FileSystem instance against the backend filesystem
> (typically HDFS) on every request. The FileSystem caching is not used as it
> does not have expiration/timeout and filesystem instances in there live
> forever, for long running services like HttpFS this is not a good thing as it
> would keep connections open to the NN.
--
This message is automatically generated by JIRA.
If you think it was sent incorrectly, please contact your JIRA administrators:
https://issues.apache.org/jira/secure/ContactAdministrators!default.jspa
For more information on JIRA, see: http://www.atlassian.com/software/jira
