[jira] [Created] (MYRIAD-215) Support serving the JVM

2016-06-03 Thread DarinJ (JIRA)
DarinJ created MYRIAD-215: - Summary: Support serving the JVM Key: MYRIAD-215 URL: https://issues.apache.org/jira/browse/MYRIAD-215 Project: Myriad Issue Type: New Feature Components:

[jira] [Comment Edited] (MYRIAD-212) Separate/Backup NodeState from the run time either using MyriadFS or Zookeeper

2016-06-03 Thread DarinJ (JIRA)
[ https://issues.apache.org/jira/browse/MYRIAD-212?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=15314625#comment-15314625 ] DarinJ edited comment on MYRIAD-212 at 6/3/16 7:15 PM: --- [~zjaffee] can you

[jira] [Commented] (MYRIAD-212) Separate/Backup NodeState from the run time either using MyriadFS or Zookeeper

2016-06-03 Thread DarinJ (JIRA)
[ https://issues.apache.org/jira/browse/MYRIAD-212?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=15314625#comment-15314625 ] DarinJ commented on MYRIAD-212: --- [~zjaffee] can you articulate why we need to keep NodeStore Resiliant? It

Re: problem getting fine grained scaling workig

2016-06-03 Thread Darin Johnson
That is correct you need at least one node manager with the minimum requirements to launch an ApplicationMaster. Otherwise YARN will throw an exception. On Fri, Jun 3, 2016 at 10:52 AM, yuliya Feldman wrote: > I believe you need at least one NM that is not subject

Re: problem getting fine grained scaling working

2016-06-03 Thread Darin Johnson
That is normal behavior, Myriad keeps the resources to flexup a node manager incase a job comes in of a few seconds and then releases them. The info statement is arguably chatty and will probably go to debug in a few more releases. On Fri, Jun 3, 2016 at 9:18 AM, Stephen Gran