You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@helix.apache.org by "Kanak Biscuitwala (JIRA)" <ji...@apache.org> on 2013/08/01 22:57:51 UTC
[jira] [Updated] (HELIX-152) Extend auto rebalance to accept
replicas with non-unit weights and constraints
[ https://issues.apache.org/jira/browse/HELIX-152?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Kanak Biscuitwala updated HELIX-152:
------------------------------------
Description:
The current auto rebalancing strategy assumes that each replica adds a one-dimensional value of 1. It may make sense to make these costs weighted and perhaps multi-dimensional. Arbitrary constraint specification is also useful.
This is similar to problems related to constraint satisfaction or knapsack solving, and some existing implementations may be worth looking at. One example: https://code.google.com/p/or-tools/
was:
The current auto rebalancing strategy assumes that each replica adds a one-dimensional value of 1. It may make sense to make these costs weighted and perhaps multi-dimensional.
This is similar to problems related to constraint satisfaction or knapsack solving, and some existing implementations may be worth looking at. One example: https://code.google.com/p/or-tools/
Summary: Extend auto rebalance to accept replicas with non-unit weights and constraints (was: Extend auto rebalance to accept replicas with non-unit weights)
> Extend auto rebalance to accept replicas with non-unit weights and constraints
> ------------------------------------------------------------------------------
>
> Key: HELIX-152
> URL: https://issues.apache.org/jira/browse/HELIX-152
> Project: Apache Helix
> Issue Type: Improvement
> Components: helix-core
> Reporter: Kanak Biscuitwala
> Priority: Minor
>
> The current auto rebalancing strategy assumes that each replica adds a one-dimensional value of 1. It may make sense to make these costs weighted and perhaps multi-dimensional. Arbitrary constraint specification is also useful.
> This is similar to problems related to constraint satisfaction or knapsack solving, and some existing implementations may be worth looking at. One example: https://code.google.com/p/or-tools/
--
This message is automatically generated by JIRA.
If you think it was sent incorrectly, please contact your JIRA administrators
For more information on JIRA, see: http://www.atlassian.com/software/jira