You are viewing a plain text version of this content. The canonical link for it is here.
Posted to dev@hive.apache.org by "Ning Zhang (JIRA)" <ji...@apache.org> on 2011/07/30 06:16:10 UTC

[jira] [Assigned] (HIVE-2202) multi-thread hive io and execution

     [ https://issues.apache.org/jira/browse/HIVE-2202?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]

Ning Zhang reassigned HIVE-2202:
--------------------------------

    Assignee: Tim Armstrong

> multi-thread hive io and execution
> ----------------------------------
>
>                 Key: HIVE-2202
>                 URL: https://issues.apache.org/jira/browse/HIVE-2202
>             Project: Hive
>          Issue Type: Improvement
>            Reporter: Namit Jain
>            Assignee: Tim Armstrong
>
> Multi-threading hive's IO part and execution part. For Hive's RCFile, the reader can be put in a separate thread, and can keep 2 blocks in memory. One block for current processing, and the other for next batch. Potentially this can be more intelligent (like determine how many threads to read depending on the execution speed), but this will depends on the HDFS client's implementation. And the writer can also put into a separate thread, this way, the execution will not need to block on writer.

--
This message is automatically generated by JIRA.
For more information on JIRA, see: http://www.atlassian.com/software/jira