hadoop-mapreduce-issues mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Owen O'Malley (JIRA)" <j...@apache.org>
Subject [jira] Commented: (MAPREDUCE-326) The lowest level map-reduce APIs should be byte oriented
Date Tue, 16 Feb 2010 16:55:28 GMT

    [ https://issues.apache.org/jira/browse/MAPREDUCE-326?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12834306#action_12834306
] 

Owen O'Malley commented on MAPREDUCE-326:
-----------------------------------------

Clearly if the argument to write is a ByteBuffer, then pipes could read straight into a DirectByteBuffer
and send it straight to the map output collector at the cost of a single copy.

{code}
void write(int partition, ByteBuffer key, ByteBuffer value) throws IOException, InterruptedException;
{code}

That still leaves serializers doing a second copy and to avoid that, you need to invert the
control and do something like:

{code}
public class RawKeyValueOutputStream extends DataOutputStream {
   public void startKey(int partition) throws IOException, InterruptedException;
   public void startValue() throws IOException, InterruptedException;
}
{code}

where you can write straight to the map output collector. Personally, I think the ByteBuffer
approach is easier, but I can see arguments both ways.

However, there is still a bigger issue. At this point we are arguing about a single method
to collect the raw map outputs. Why should we introduce a new level of abstraction that our
users *absolutely* don't need? Wouldn't it make more sense to just add the method to MapContext
to collect raw outputs?


> The lowest level map-reduce APIs should be byte oriented
> --------------------------------------------------------
>
>                 Key: MAPREDUCE-326
>                 URL: https://issues.apache.org/jira/browse/MAPREDUCE-326
>             Project: Hadoop Map/Reduce
>          Issue Type: Improvement
>            Reporter: eric baldeschwieler
>         Attachments: MAPREDUCE-326-api.patch, MAPREDUCE-326.pdf
>
>
> As discussed here:
> https://issues.apache.org/jira/browse/HADOOP-1986#action_12551237
> The templates, serializers and other complexities that allow map-reduce to use arbitrary
types complicate the design and lead to lots of object creates and other overhead that a byte
oriented design would not suffer.  I believe the lowest level implementation of hadoop map-reduce
should have byte string oriented APIs (for keys and values).  This API would be more performant,
simpler and more easily cross language.
> The existing API could be maintained as a thin layer on top of the leaner API.

-- 
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the issue online.


Mime
View raw message