[ 
https://issues.apache.org/jira/browse/HDDS-1266?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16816882#comment-16816882
 ] 

Yiqun Lin commented on HDDS-1266:
---------------------------------

{quote}Balancer At this point, we can wonder if the random placement model 
should be the model used for the distribution of blocks. The HDFS admins could 
be running balancer, and balancer does not obey the first node, differ- ent 
rack, same rack algorithm...
{quote}
Catching one place, above description for balancer is not right. The Balancer 
will follow the placement strategy when moving blocks. Can see the related 
function: 
[org|eclipse-javadoc:%E2%98%82=hadoop-hdfs/src%5C/main%5C/java%3Corg].[apache|eclipse-javadoc:%E2%98%82=hadoop-hdfs/src%5C/main%5C/java%3Corg.apache].[hadoop|eclipse-javadoc:%E2%98%82=hadoop-hdfs/src%5C/main%5C/java%3Corg.apache.hadoop].[hdfs|eclipse-javadoc:%E2%98%82=hadoop-hdfs/src%5C/main%5C/java%3Corg.apache.hadoop.hdfs].[server|eclipse-javadoc:%E2%98%82=hadoop-hdfs/src%5C/main%5C/java%3Corg.apache.hadoop.hdfs.server].[balancer|eclipse-javadoc:%E2%98%82=hadoop-hdfs/src%5C/main%5C/java%3Corg.apache.hadoop.hdfs.server.balancer].[Dispatcher|eclipse-javadoc:%E2%98%82=hadoop-hdfs/src%5C/main%5C/java%3Corg.apache.hadoop.hdfs.server.balancer%7BDispatcher.java%E2%98%83Dispatcher]#isGoodBlockCandidate.
 It can be used for distributing the blocks but not means it''s just a random 
placement way.

> [Ozone upgrade] Support Upgrading HDFS clusters to use Ozone
> ------------------------------------------------------------
>
>                 Key: HDDS-1266
>                 URL: https://issues.apache.org/jira/browse/HDDS-1266
>             Project: Hadoop Distributed Data Store
>          Issue Type: New Feature
>            Reporter: Anu Engineer
>            Assignee: Anu Engineer
>            Priority: Major
>         Attachments: InPlaceUpgradesForOzone.pdf
>
>
> This is the master JIRA to support upgrading existing HDFS clusters to have 
> Ozone running concurrently. One of the requirements is that we support 
> upgrading from HDFS to Ozone, without a full data copy. This requirement is 
> called "In Place upgrade", the end result of such an upgrade would be to have 
> the HDFS data appear in Ozone as if Ozone has taken a snap-shot of the HDFS 
> data. Once upgrade is complete, Ozone and HDFS will act as independent 
> systems. I will post a design document soon.



--
This message was sent by Atlassian JIRA
(v7.6.3#76005)

---------------------------------------------------------------------
To unsubscribe, e-mail: hdfs-issues-unsubscr...@hadoop.apache.org
For additional commands, e-mail: hdfs-issues-h...@hadoop.apache.org

Reply via email to