You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@bigtop.apache.org by "YoungWoo Kim (Jira)" <ji...@apache.org> on 2019/10/16 15:18:00 UTC
[jira] [Commented] (BIGTOP-3233) Batch scheduler for long running
ML and big data workload
[ https://issues.apache.org/jira/browse/BIGTOP-3233?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16952914#comment-16952914 ]
YoungWoo Kim commented on BIGTOP-3233:
--------------------------------------
I think deploying volcano via Helm with custom values.yaml would be a easy way to do this...also Spark operator integration with volcano would be good too! ref: BIGTOP-3255
> Batch scheduler for long running ML and big data workload
> ---------------------------------------------------------
>
> Key: BIGTOP-3233
> URL: https://issues.apache.org/jira/browse/BIGTOP-3233
> Project: Bigtop
> Issue Type: Sub-task
> Reporter: YoungWoo Kim
> Priority: Major
>
> Batch scheduling or resource intensive workload is common pattern in big data analytics world. Certain situation, we should support spark or flink jobs with batch scheduler on k8s.
> Refs.
> - https://github.com/volcano-sh/volcano
> - https://github.com/kubernetes-sigs/kube-batch
--
This message was sent by Atlassian Jira
(v8.3.4#803005)