[ 
https://issues.apache.org/jira/browse/KUDU-3476?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17907123#comment-17907123
 ] 

derek.huang commented on KUDU-3476:
-----------------------------------

Hi [~aserbin],

Thanks for the info.

I went through the code and found that it actually would work by merely 
removing the check for the number of tables in --tables flag when range 
rebalancing is enabled. Previously, when a non range partitioned table is 
passed in --tables, it will be treated like a table with a single range 
partition whose start key is an empty string.

I have uploaded a patch allowing multiple tables in --tables flag. I also 
updated the output of table distribution details when range rebalancing is 
applied to to multiple tables with mixed partition schema. The patch is 
available at [https://gerrit.cloudera.org/#/c/22239/] . Could you please take a 
look?

Thanks.

> Make replica placement range and table aware
> --------------------------------------------
>
>                 Key: KUDU-3476
>                 URL: https://issues.apache.org/jira/browse/KUDU-3476
>             Project: Kudu
>          Issue Type: New Feature
>          Components: master, tserver
>            Reporter: Mahesh Reddy
>            Assignee: Mahesh Reddy
>            Priority: Major
>             Fix For: 1.17.0
>
>
> The current replica placement algorithm uses the power of two choices 
> algorithm. This algorithm randomly selects tservers and places the replica on 
> the tserver with less replicas. This can lead to potential hotspotting as it 
> doesn't discriminate by range or table so many tablets from the same 
> range/table can be disproportionally distributed.
> With this new feature, the replicas will be placed in a way that the tablets 
> per range will be equally distributed amongst the available tservers. If 
> multiple tservers have the same amount of replicas per range, then the 
> tserver with less replicas for that table will be selected. If multiple 
> tservers have the same amount of replicas for that table, the tserver with 
> less total replicas will be chosen.



--
This message was sent by Atlassian Jira
(v8.20.10#820010)

Reply via email to