You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@spark.apache.org by "Xiangrui Meng (JIRA)" <ji...@apache.org> on 2015/05/14 21:41:59 UTC
[jira] [Closed] (SPARK-7642) Missing 1 worker on standalone
clusters.
[ https://issues.apache.org/jira/browse/SPARK-7642?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Xiangrui Meng closed SPARK-7642.
--------------------------------
Resolution: Not A Problem
I used "launch more like this" to increase the cluster size to 16. The original slave node may be inconsistent with others, which causes the missing work on 1.4. I'm closing this JIRA.
> Missing 1 worker on standalone clusters.
> ----------------------------------------
>
> Key: SPARK-7642
> URL: https://issues.apache.org/jira/browse/SPARK-7642
> Project: Spark
> Issue Type: Bug
> Components: Deploy, Spark Core
> Affects Versions: 1.4.0
> Reporter: Xiangrui Meng
> Assignee: Xiangrui Meng
> Priority: Blocker
> Attachments: 1.3 data distribution.png, 1.4 data distribution.png
>
>
> Saw this weird issue during performance test. I have a 16-node (plus 1 master) standalone cluster on EC2. I saw 16 works on the master page (:8080). When I run a job, in the executor tab I saw 17 executors (including the driver) in 1.3. However, this number becomes 16 (also including the driver) in 1.4. So one worker is missing from the cluster in 1.4.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscribe@spark.apache.org
For additional commands, e-mail: issues-help@spark.apache.org