[
https://issues.apache.org/jira/browse/HBASE-17282?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Duo Zhang updated HBASE-17282:
------------------------------
Attachment: HBASE-17282.patch
The first version. Busy these days so put it here to get some feedback first.
Need to add testcase to test if the concurrency limitation works.
> Reduce the redundant requests to meta table
> -------------------------------------------
>
> Key: HBASE-17282
> URL: https://issues.apache.org/jira/browse/HBASE-17282
> Project: HBase
> Issue Type: Sub-task
> Components: Client
> Reporter: Duo Zhang
> Fix For: 2.0.0
>
> Attachments: HBASE-17282.patch
>
>
> This usually happens at startup when the meta cache is empty. There will be a
> lot of locating requests, but most of will have same results. Things become
> worse if we do batch operations with AsyncTable as we will send a locating
> request for each operation concurrently.
> We need to reduce the redundant requests to meta table.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
