[
https://issues.apache.org/jira/browse/HBASE-7932?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13652323#comment-13652323
]
stack commented on HBASE-7932:
------------------------------
Is this comment right?
+ // Only read favored nodes if using the assignment-based load balancer.
Do you meant the favored nodes balancer?
This is probably plain to you but maybe it needs to be drawn out more that the
favored nodes load balancer is but a stepping stone? What we really want is a
stocastic balancer that is favored nodes aware? Just saying....
Is that a lookup against meta each time we assign a region? If so, won't we be
slowing assign especially if slow meta? Data will be offline longer? Maybe
its not too bad... but probably worth caching favored nodes info or doing the
update out-of-bound with assign? (could be in subsequent patch but I think you
need to note that this look up can take time).
What did our facebook brothers and sisters do here? Do you know boss?
Otherwise patch is coming along nicely
> Do the necessary plumbing for the region locations in META table and send the
> info to the RegionServers
> -------------------------------------------------------------------------------------------------------
>
> Key: HBASE-7932
> URL: https://issues.apache.org/jira/browse/HBASE-7932
> Project: HBase
> Issue Type: Sub-task
> Reporter: Devaraj Das
> Assignee: Devaraj Das
> Priority: Critical
> Fix For: 0.95.1
>
> Attachments: 7932-1.patch, 7932-3.patch, 7932-8.1.patch,
> 7932-8.patch, 7932-simple-2.patch, 7932-simple-with-meta-pb.1.txt,
> 7932-simple-with-meta-pb.2.txt, 7932-wip-2.patch, 7932-wip-3.patch,
> 7932-wip-4.patch, 7932-wip.patch
>
>
--
This message is automatically generated by JIRA.
If you think it was sent incorrectly, please contact your JIRA administrators
For more information on JIRA, see: http://www.atlassian.com/software/jira
