[
https://issues.apache.org/jira/browse/HADOOP-7445?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13066013#comment-13066013
]
Kihwal Lee commented on HADOOP-7445:
------------------------------------
Sorry, probably I wasn't very clear. I didn't mean to suggest jamming
everything into one. I was thinking about exposing a set of pure native
functions at multi-chunk checksum processing level in addition to single chunk
processing. I imagine this level of abstraction is good enough for the native
client code. If we can separate JNI-wrapper bits from these, the native
functions can go to their own C file(s) and function prototypes in header(s).
The rest is up to the build system. The build system can make it part of
libhadoop or make it an independent lib or be part of native executables or
whatever. As for inlining/optimization, we can optimize within the multi-chunk
functions and that should be good enough for most use cases. Does it make sense?
> Implement bulk checksum verification using efficient native code
> ----------------------------------------------------------------
>
> Key: HADOOP-7445
> URL: https://issues.apache.org/jira/browse/HADOOP-7445
> Project: Hadoop Common
> Issue Type: Improvement
> Components: native, util
> Reporter: Todd Lipcon
> Assignee: Todd Lipcon
> Attachments: hadoop-7445.txt, hadoop-7445.txt
>
>
> Once HADOOP-7444 is implemented ("bulk" API for checksums), good performance
> gains can be had by implementing bulk checksum operations using JNI. This
> JIRA is to add checksum support to the native libraries. Of course if native
> libs are not available, it will still fall back to the pure-Java
> implementations.
--
This message is automatically generated by JIRA.
For more information on JIRA, see: http://www.atlassian.com/software/jira
