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

Posted to issues@hive.apache.org by "Ádám Szita (Jira)" <ji...@apache.org> on 2020/02/03 15:26:00 UTC

[jira] [Assigned] (HIVE-22820) Proactive LLAP cache eviction

     [ https://issues.apache.org/jira/browse/HIVE-22820?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]

Ádám Szita reassigned HIVE-22820:
---------------------------------


> Proactive LLAP cache eviction
> -----------------------------
>
>                 Key: HIVE-22820
>                 URL: https://issues.apache.org/jira/browse/HIVE-22820
>             Project: Hive
>          Issue Type: Improvement
>          Components: llap
>            Reporter: Ádám Szita
>            Assignee: Ádám Szita
>            Priority: Major
>
> Currently LLAP cache eviction is only based on an eviction policy, that is reactive in a way that it only evicts buffers whenever there's space required for new ones.
> It does not take for example dropped entities (partitions, tables or even dbs) into consideration. We should also implement a proactive side of the eviction that does this for us, and in turn could increase overall cache hit ratios.



--
This message was sent by Atlassian Jira
(v8.3.4#803005)