[
https://issues.apache.org/jira/browse/HADOOP-3672?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12613495#action_12613495
]
Raghu Angadi commented on HADOOP-3672:
--------------------------------------
> Perhaps a separate issue should be filed to explore what would be needed for
> RPC to be usable by the mapred shuffle?
Thats right, we should first list the requirements in the new jira. I can
surely list good-to-haves for HDFS transfers.
> I don't think so. It calls their write(OutputStream) methods. [...]
:). It does, but OutputStream is a {{DataOutputBuffer()}}. see Client.java:476.
Similarly on the server, we first read/write the data to a single buffer.
> support for persistent connections to improve random read performance.
> ----------------------------------------------------------------------
>
> Key: HADOOP-3672
> URL: https://issues.apache.org/jira/browse/HADOOP-3672
> Project: Hadoop Core
> Issue Type: Improvement
> Components: dfs
> Affects Versions: 0.17.0
> Environment: Linux 2.6.9-55 , Dual Core Opteron 280 2.4Ghz , 4GB
> memory
> Reporter: George Wu
> Attachments: pread_test.java
>
>
> preads() establish new connections per request. yourkit java profiles show
> that this connection overhead is pretty significant on the DataNode.
> I wrote a simple microbenchmark program which does many iterations of pread()
> from different offsets of a large file. I hacked DFSClient/DataNode code to
> re-use the same connection/DataNode request handler thread. The performance
> improvement was 7% when the data is served from disk and 80% when the data is
> served from the OS page cache.
--
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the issue online.
