[
https://issues.apache.org/jira/browse/HDFS-755?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12787224#action_12787224
]
Todd Lipcon commented on HDFS-755:
----------------------------------
I checked Raghu's idea and it's correct - since there's a buffer in BlockReader
and it does some small reads at the beginning of the block (to get status code,
etc) it "misaligns" the reads. I'm benchmarking various values for this buffer
now with similar benchmarks as I ran in HADOOP-3205. (that JIRA should still be
fine to commit)
> Read multiple checksum chunks at once in DFSInputStream
> -------------------------------------------------------
>
> Key: HDFS-755
> URL: https://issues.apache.org/jira/browse/HDFS-755
> Project: Hadoop HDFS
> Issue Type: Improvement
> Components: hdfs client
> Affects Versions: 0.22.0
> Reporter: Todd Lipcon
> Assignee: Todd Lipcon
> Attachments: hdfs-755.txt, hdfs-755.txt, hdfs-755.txt, hdfs-755.txt,
> hdfs-755.txt
>
>
> HADOOP-3205 adds the ability for FSInputChecker subclasses to read multiple
> checksum chunks in a single call to readChunk. This is the HDFS-side use of
> that new feature.
--
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the issue online.
