[
https://issues.apache.org/jira/browse/HIVE-9418?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14298170#comment-14298170
]
Sergey Shelukhin commented on HIVE-9418:
----------------------------------------
I think I will change to return RGx all cols from lower layer, rather than by
column, because that's how we will read. Before high-level cache, we'd not have
the cost of separating that by column to cache.
In general, high level cache if any will need rethinking, because there are
multiple streams per column, and some of them are shared across all RGs (e.g.
dictionary).
For now low level cache is probably the best idea.
> LLAP: ORC production of encoded data, cache usage
> -------------------------------------------------
>
> Key: HIVE-9418
> URL: https://issues.apache.org/jira/browse/HIVE-9418
> Project: Hive
> Issue Type: Sub-task
> Reporter: Sergey Shelukhin
> Assignee: Sergey Shelukhin
>
> ORC needs to be able to read self-contained rowgroups and return them. It
> should use low-level cache in process. In future, we may use high-level cache
> to cache rowgroups instead
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
