You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@spark.apache.org by "Marcelo Vanzin (JIRA)" <ji...@apache.org> on 2017/05/30 23:12:04 UTC

[jira] [Resolved] (SPARK-20651) Speed up the new app state listener

     [ https://issues.apache.org/jira/browse/SPARK-20651?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]

Marcelo Vanzin resolved SPARK-20651.
------------------------------------
    Resolution: Won't Do

I've done some perf work to make sure live applications don't regress, and made a bunch of changes that make the original code I had for this milestone obsolete, so I removed it from my plan.

The current list of "upcoming" PRs can be seen at:
https://github.com/vanzin/spark/pulls

> Speed up the new app state listener
> -----------------------------------
>
>                 Key: SPARK-20651
>                 URL: https://issues.apache.org/jira/browse/SPARK-20651
>             Project: Spark
>          Issue Type: Sub-task
>          Components: Spark Core
>    Affects Versions: 2.3.0
>            Reporter: Marcelo Vanzin
>
> See spec in parent issue (SPARK-18085) for more details.
> This task tracks enhancements to the code added in previous tasks so that the new app state listener is faster; it adds a caching layer and an asynchronous write layer that also does deduplication, so that it avoids blocking the listener thread and also avoids unnecessary writes to disk.



--
This message was sent by Atlassian JIRA
(v6.3.15#6346)

---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscribe@spark.apache.org
For additional commands, e-mail: issues-help@spark.apache.org