You are viewing a plain text version of this content. The canonical link for it is here.

Posted to dev@hive.apache.org by "Matt McCline (JIRA)" <ji...@apache.org> on 2017/07/25 12:25:00 UTC

[jira] [Created] (HIVE-17164) Vectorization: Support PTF (Part 2: Unbounded Support-- Turn on by default)

Matt McCline created HIVE-17164:
-----------------------------------

             Summary: Vectorization: Support PTF (Part 2: Unbounded Support-- Turn on by default)
                 Key: HIVE-17164
                 URL: https://issues.apache.org/jira/browse/HIVE-17164
             Project: Hive
          Issue Type: Bug
          Components: Hive
            Reporter: Matt McCline
            Assignee: Matt McCline
            Priority: Critical


Add disk storage backing.  Turn hive.vectorized.execution.ptf.enabled on by default.

Add hive.vectorized.ptf.max.memory.buffering.batch.count to specify the maximum number of vectorized row batch to buffer in memory before spilling to disk.

Add hive.vectorized.testing.reducer.batch.size parameter to have the Tez Reducer make small batches for making a lot of key group batches that cause memory buffering and disk storage backing.



--
This message was sent by Atlassian JIRA
(v6.4.14#64029)