You are viewing a plain text version of this content. The canonical link for it is here.
Posted to dev@sdap.apache.org by "ASF GitHub Bot (Jira)" <ji...@apache.org> on 2019/12/02 21:30:00 UTC

[jira] [Work logged] (SDAP-215) Fix performance issues with Spark on Kubernetes

     [ https://issues.apache.org/jira/browse/SDAP-215?focusedWorklogId=352230&page=com.atlassian.jira.plugin.system.issuetabpanels:worklog-tabpanel#worklog-352230 ]

ASF GitHub Bot logged work on SDAP-215:
---------------------------------------

                Author: ASF GitHub Bot
            Created on: 02/Dec/19 21:29
            Start Date: 02/Dec/19 21:29
    Worklog Time Spent: 10m 
      Work Description: eamonford commented on pull request #88: SDAP-215 Use k8s as Spark scheduler and create helm chart
URL: https://github.com/apache/incubator-sdap-nexus/pull/88
 
 
   This branch updates Spark to v2.4.4 to be natively compatible with Kubernetes, so Spark now uses Kubernetes as a scheduler. This branch also adds a Helm chart so that nexus can be deployed using helm install.
 
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
 
For queries about this service, please contact Infrastructure at:
users@infra.apache.org


Issue Time Tracking
-------------------

            Worklog Id:     (was: 352230)
    Remaining Estimate: 0h
            Time Spent: 10m

> Fix performance issues with Spark on Kubernetes
> -----------------------------------------------
>
>                 Key: SDAP-215
>                 URL: https://issues.apache.org/jira/browse/SDAP-215
>             Project: Apache Science Data Analytics Platform
>          Issue Type: Improvement
>          Components: nexus
>            Reporter: Eamon Ford
>            Priority: Major
>          Time Spent: 10m
>  Remaining Estimate: 0h
>
> When running Spark algorithms on a Kubernetes deployment of SDAP, performance is slow and Spark is constrained to using a single Kubernetes pod. Upgrade the Spark version and change the deployment so that Spark can use Kubernetes as its scheduler.



--
This message was sent by Atlassian Jira
(v8.3.4#803005)