[
https://issues.apache.org/jira/browse/SPARK-6707?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15326297#comment-15326297
]
Fan Du commented on SPARK-6707:
-------------------------------
Hi [~ankurcha]
I have one query about the example, {{tachyon=true;us-east-1=false}}, in the
ticket message,
I assume tachyon is memory-centric distributed storage system, which is now
renamed to Alluxio,
Alluxio can run on Mesos too, so back to my question:
Does {{tachyon=true;us-east-1=false}} indicate application prefer nodes which
already runs tachyon on them?
IOW, applications has affinity between each other?
I'm asking this because I'm working on a similar feature, which would enable
Mesos framework the ability to update attributes in
[MESOS-5545|https://issues.apache.org/jira/browse/MESOS-5545#], I think your
comments could possibly justify such requirement.
> Mesos Scheduler should allow the user to specify constraints based on slave
> attributes
> --------------------------------------------------------------------------------------
>
> Key: SPARK-6707
> URL: https://issues.apache.org/jira/browse/SPARK-6707
> Project: Spark
> Issue Type: Improvement
> Components: Mesos, Scheduler
> Affects Versions: 1.3.0
> Reporter: Ankur Chauhan
> Assignee: Ankur Chauhan
> Labels: mesos, scheduler
> Fix For: 1.5.0
>
>
> Currently, the mesos scheduler only looks at the 'cpu' and 'mem' resources
> when trying to determine the usablility of a resource offer from a mesos
> slave node. It may be preferable for the user to be able to ensure that the
> spark jobs are only started on a certain set of nodes (based on attributes).
> For example, If the user sets a property, let's say
> {code}spark.mesos.constraints{code} is set to
> {code}tachyon=true;us-east-1=false{code}, then the resource offers will be
> checked to see if they meet both these constraints and only then will be
> accepted to start new executors.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org
For additional commands, e-mail: issues-h...@spark.apache.org
