[
https://issues.apache.org/jira/browse/HBASE-13323?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14393664#comment-14393664
]
Andrew Purtell commented on HBASE-13323:
----------------------------------------
bq. You're running HBase on top of HDFS so you have to live with the quirks of
HDFS (balancer, worm, etc ...)
Yes.
bq. HDFS-7967 is a symptom of not thinking about the underlying FS and its
impact on HBase.
Maybe you are thinking of another issue? I don't think HBase is involved on
that one.
If you can't run the balancer on a large cluster because it will mount a DoS on
the NameNode, it should be considered harmful. But that's an implementation
problem that can be fixed.
I don't think the balancer is a problem for HBase as long as you're running a
recent enough HDFS including HDFS-6133.
> Audit behavior heterogenous node capacity
> -----------------------------------------
>
> Key: HBASE-13323
> URL: https://issues.apache.org/jira/browse/HBASE-13323
> Project: HBase
> Issue Type: Task
> Components: Balancer
> Reporter: Nick Dimiduk
> Labels: beginner
>
> From the thread "introducing nodes w/ more storage"
> (http://search-hadoop.com/m/DHED4azyle2), we should have a look at what
> happens when nodes of varying data density are used in a single cluster. The
> user would expect that nodes be filled according to their capacity, meaning
> an "even distribution" looks like all nodes at the same pct use. This
> behavior is probably in the intersection of hbase balancer and hdfs balancer.
> Probably this is made more complex by recent HDFS features such as HDFS-5682.
> After investigation, let's fix it up to work better (if it's broken), and
> document the behavior in our awesome book.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
