[
https://issues.apache.org/jira/browse/MESOS-4666?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15144942#comment-15144942
]
Anindya Sinha edited comment on MESOS-4666 at 2/14/16 6:57 AM:
---------------------------------------------------------------
We can expose `repeated Resource total_resources` in the protobuf `Offer` to
notify frameworks of the maximum resources. This would be a summation of all
resources based on cpu, mem, disk, etc. across all roles (+ unreserved), and
would be the value that mesos-slave was started (either via
{noformat}--resources {noformat} flag, or derived from system resources).
To preserve the existing behavior, the total_resources can be a opt-in via a
new `FrameworkInfo::Capability` set at registration of frameworks, or we could
make it a slave flag as well (defaulting to current behavior of not exposing
total_resources in Offer).
was (Author: anindya.sinha):
We can expose `repeated Resource total_resources` in the protobuf `Offer` to
notify frameworks of the maximum resources. This would be a summation of all
resources based on cpu, mem, disk, etc. across all roles (+ unreserved), and
would be the value that mesos-slave was started (either via {noformat
}--resources {noformat} flag, or derived from system resources).
To preserve the existing behavior, the total_resources can be a opt-in via a
new `FrameworkInfo::Capability` set at registration of frameworks, or we could
make it a slave flag as well (defaulting to current behavior of not exposing
total_resources in Offer).
> Expose total resources of a slave in offer for scheduling decisions
> -------------------------------------------------------------------
>
> Key: MESOS-4666
> URL: https://issues.apache.org/jira/browse/MESOS-4666
> Project: Mesos
> Issue Type: Improvement
> Components: general
> Affects Versions: 0.25.0
> Reporter: Anindya Sinha
> Assignee: Anindya Sinha
> Priority: Minor
>
> To effectively schedule certain class of tasks, the scheduler might need to
> know not only the available resources (as exposed currently) but also the
> maximum resources available on that slave. This is specifically true for
> clusters having different configurations of the slave nodes in terms of
> resources such as cpu, memory, disk, etc.
> Certain class of tasks might have a need to be scheduled on the same slave
> (esp needing shared persistent volumes, MESOS-3421). Instead of dedicating a
> slave to a framework, the framework can make a very good determination if it
> had exposure to both available as well as total resources.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
