[
https://issues.apache.org/jira/browse/SLIDER-82?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14539505#comment-14539505
]
Steve Loughran commented on SLIDER-82:
--------------------------------------
I'm thinking we can do it in Slider. This lets us use node failure history in
the placement requests, allow us to decide if/when to permit same-host
deployment. Doing it in slider will allow us to do this to run on existing
"ODP-compliant " hadoop 2.6 clusters, rather than waiting for a YARN feature
and requiring cluster upgrades.
We will have to read in topology information; this includes picking up any
information on failure domains to try and spread load away from hosts that
share same failure risks (e.g. multiple servers in a 1U/2U unit sharing power
and network)
> Support ANTI_AFFINITY_REQUIRED option
> -------------------------------------
>
> Key: SLIDER-82
> URL: https://issues.apache.org/jira/browse/SLIDER-82
> Project: Slider
> Issue Type: Task
> Components: appmaster
> Reporter: Steve Loughran
> Fix For: Slider 2.0.0
>
>
> slider has an anti-affinity flag in roles (visible in resources.json?), which
> is ignored.
> YARN-1042 promises this for YARN, slider will need
> # flag in resources.json
> # use in container requests
> we may also want two policies: anti-affinity-desired, and -required. Then if
> required nodes get >1 container for the same component type on the same node,
> it'd have to request a new one and return the old one (Risk: getting the same
> one back).
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
