[
https://issues.apache.org/jira/browse/HBASE-15648?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15258967#comment-15258967
]
Elliott Clark commented on HBASE-15648:
---------------------------------------
This one probably needs to be un-scheduled. It's a good idea. Using a lock to
make sure that there aren't too many outstanding meta requests. However since
the keys used are user specified the current implementation doesn't work.
> Reduce number of concurrent region location lookups when MetaCache entry is
> cleared
> -----------------------------------------------------------------------------------
>
> Key: HBASE-15648
> URL: https://issues.apache.org/jira/browse/HBASE-15648
> Project: HBase
> Issue Type: Sub-task
> Components: Client
> Affects Versions: 1.3.0
> Reporter: Mikhail Antonov
> Assignee: Mikhail Antonov
> Attachments: HBASE-15648-branch-1.3.v1.patch
>
>
> It seems in HConnectionImplementation#locateRegionInMeta if region location
> is removed from the cache, with large number of client threads we could have
> many of them getting cache miss and doing meta scan, which looks unnecessary
> - we could empty mechanism similar to what we have in IdLock in HFileReader
> to fetch the block to cache, do ensure that if one thread is already looking
> up location for region R1, other threads who need it's location wait until
> first thread finishes his work.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
