[
https://issues.apache.org/jira/browse/HIVE-6613?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Siddharth Seth updated HIVE-6613:
---------------------------------
Attachment: HIVE-6613.2.txt
Updated patch.
Changed cacheAccess to accept a configuration.
Haven't changed the way Inputs are cached - since this gives a way to iterate
over cached inputs, which may be useful at some point.
Removed the LocalWork check. I'm not sure if a special check is required in
case of a Bucketed Map Join.
> Control when spcific Inputs / Outputs are started
> -------------------------------------------------
>
> Key: HIVE-6613
> URL: https://issues.apache.org/jira/browse/HIVE-6613
> Project: Hive
> Issue Type: Improvement
> Reporter: Siddharth Seth
> Assignee: Siddharth Seth
> Attachments: HIVE-6613.2.txt, TEZ-6613.1.txt
>
>
> When running with Tez - a couple of enhancement are possible
> 1) Avoid re-fetching data in case of MapJoins - since the data is likely to
> be cached after the first run (container re-use for the same query)
> 2) Start Outputs only after required Inputs are ready - specifically useful
> in case of Reduce - where shuffle requires a large memory, and the Output (if
> it's a sorted output) also requires a fair amount of memory.
--
This message was sent by Atlassian JIRA
(v6.2#6252)
