[
https://issues.apache.org/jira/browse/HBASE-18246?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Stephen Yuan Jiang updated HBASE-18246:
---------------------------------------
Summary: Proc-V2 AM: Maintain Data locality in ServerCrashProcedure (was:
Maintain Data locality in ServerCrashProcedure)
> Proc-V2 AM: Maintain Data locality in ServerCrashProcedure
> ----------------------------------------------------------
>
> Key: HBASE-18246
> URL: https://issues.apache.org/jira/browse/HBASE-18246
> Project: HBase
> Issue Type: Sub-task
> Components: Region Assignment
> Affects Versions: 2.0.0
> Reporter: Stephen Yuan Jiang
> Assignee: Stephen Yuan Jiang
> Fix For: 2.0.0
>
>
> Before HBASE-18036, SSH would use round-robin to re-distribute regions during
> processing. Round-robin assignment would loss data locality. HBASE-18036
> retains data locality if the dead region server has already restarted when
> the dead RS is processing.
> With Proc-V2 based AM, the change of HBASE-18036 in Apache HBASE 1.x releases
> is no longer possible. We need to implement the same logic under Proc-V2
> based AM.
--
This message was sent by Atlassian JIRA
(v6.4.14#64029)
