[
https://issues.apache.org/jira/browse/HDFS-755?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Todd Lipcon updated HDFS-755:
-----------------------------
Attachment: hdfs-755.txt
Here's an updated patch which fixes some behavior when running against an
unpatched Common. If Common includes HADOOP-3205, it will be faster, and if it
doesn't include HADOOP-3205, it should still work at the old speed.
I also ran some more benchmarks over lunch, running "fs -cat bigfile bigfile
bigfile ...20 times..." repeatedly with and without the patch. This differs
from my previous benchmark in that each JVM runs for a good 40-50 seconds -
enough time to fully JIT the code, etc. The patch is about a 3.4% speedup
compared to trunk for these long reads as well (at 95% significance level).
> 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
>
>
> 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.
