[
https://issues.apache.org/jira/browse/HDFS-6133?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14318451#comment-14318451
]
Yongjun Zhang commented on HDFS-6133:
-------------------------------------
Hi [~zhaoyunjiong],
{quote}
Sorry, which question? I clicked the URL, but don't show the question clearly.
{quote}
A couple of days ago, I replied your comment as below (if you roll up to find
my comment you will see):
{quote}
Are you saying NumFavouredNodes is equivalent to replication factor? I thought
they are different: the favoredNodes is specified when constructing
DFSOutputStream, as a collection of DNs. The write pipeline of a data block
usually has three replicas, if any of the replicas happens to be in the
collection, and the data is pinned there.
I guess what you meant is that the normal use cases are, when we construct
DFSOutputStream for a file, we usually only pass replication number of DNs as
favored DNs? Is there use scenario that one want to specify larger number of
favoredNodes?
{quote}
Thanks.
> Make Balancer support exclude specified path
> --------------------------------------------
>
> Key: HDFS-6133
> URL: https://issues.apache.org/jira/browse/HDFS-6133
> Project: Hadoop HDFS
> Issue Type: Improvement
> Components: balancer & mover, datanode
> Reporter: zhaoyunjiong
> Assignee: zhaoyunjiong
> Fix For: 2.7.0
>
> Attachments: HDFS-6133-1.patch, HDFS-6133-10.patch,
> HDFS-6133-11.patch, HDFS-6133-2.patch, HDFS-6133-3.patch, HDFS-6133-4.patch,
> HDFS-6133-5.patch, HDFS-6133-6.patch, HDFS-6133-7.patch, HDFS-6133-8.patch,
> HDFS-6133-9.patch, HDFS-6133.patch
>
>
> Currently, run Balancer will destroying Regionserver's data locality.
> If getBlocks could exclude blocks belongs to files which have specific path
> prefix, like "/hbase", then we can run Balancer without destroying
> Regionserver's data locality.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
