You are viewing a plain text version of this content. The canonical link for it is here.
Posted to hdfs-dev@hadoop.apache.org by "Amos Bird (JIRA)" <ji...@apache.org> on 2016/12/16 08:44:58 UTC
[jira] [Created] (HDFS-11256) Rebalance specific directory
Amos Bird created HDFS-11256:
--------------------------------
Summary: Rebalance specific directory
Key: HDFS-11256
URL: https://issues.apache.org/jira/browse/HDFS-11256
Project: Hadoop HDFS
Issue Type: New Feature
Components: balancer & mover
Affects Versions: 3.0.0-alpha1
Reporter: Amos Bird
Fix For: 3.0.0-alpha1
Currently hdfs only supports rebalancing over entire cluster. This might not be utilized by data processing systems like hive, spark, impala etl.
In hive, we may need to maximize some fact tables IO performance by carefully sharding their blocks evenly over all disks. Normally a INSERT SELECT is done to achieve such redistributing progress.
Given a table is backed by one directory on hdfs, rebalancing specific dir may be very useful.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
---------------------------------------------------------------------
To unsubscribe, e-mail: hdfs-dev-unsubscribe@hadoop.apache.org
For additional commands, e-mail: hdfs-dev-help@hadoop.apache.org