You are viewing a plain text version of this content. The canonical link for it is here.

Posted to dev@helix.apache.org by kishore g <g....@gmail.com> on 2015/03/05 23:01:01 UTC

Re: [jira] [Updated] (HELIX-571) Rack-aware rebalancer

Is the idea to use the rack Id info in our rebalancers?

On Wed, Mar 4, 2015 at 1:46 PM, Zhen Zhang (JIRA) <ji...@apache.org> wrote:

>
>      [
> https://issues.apache.org/jira/browse/HELIX-571?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
> ]
>
> Zhen Zhang updated HELIX-571:
> -----------------------------
>     Description: If rack information is available, we sometimes need to
> put replica of the same partition on different racks to avoid them sharing
> the same failure domain. This is a serious concern especially when rack has
> a single switch.  (was: If rack information is available, we sometimes need
> to put replica of the same partition different racks to avoid them sharing
> the same failure domain. This is a serious concern especially when rack has
> a single switch.)
>
> > Rack-aware rebalancer
> > ---------------------
> >
> >                 Key: HELIX-571
> >                 URL: https://issues.apache.org/jira/browse/HELIX-571
> >             Project: Apache Helix
> >          Issue Type: Bug
> >            Reporter: Zhen Zhang
> >
> > If rack information is available, we sometimes need to put replica of
> the same partition on different racks to avoid them sharing the same
> failure domain. This is a serious concern especially when rack has a single
> switch.
>
>
>
> --
> This message was sent by Atlassian JIRA
> (v6.3.4#6332)
>