[jira] [Comment Edited] (STORM-2083) Blacklist Scheduler

["Jungtaek Lim (JIRA)" <ji...@apache.org>]

    [ https://issues.apache.org/jira/browse/STORM-2083?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16174987#comment-16174987 ] 

Jungtaek Lim edited comment on STORM-2083 at 9/21/17 3:51 PM:
--------------------------------------------------------------

[~howardhl]
Hi, I think Github mention wouldn't work for most of us, so leaving kindly reminder from JIRA. Could you spend time to continue working on PR to finalize? 
If you can't or you don't want by yourself please let me know so that I can take over with preserving your credit. 
Thanks in advance!


was (Author: kabhwan):
[~howardhl]
Hi, I think Github mention wouldn't work for most of us, so leaving kindly reminder. Could you spend time to continue working on PR to finalize? 
If you can't or you don't want by yourself please let me know so that I can take over with preserving your credit. 
Thanks in advance!

> Blacklist Scheduler
> -------------------
>
>                 Key: STORM-2083
>                 URL: https://issues.apache.org/jira/browse/STORM-2083
>             Project: Apache Storm
>          Issue Type: New Feature
>          Components: storm-core
>            Reporter: Howard Lee
>              Labels: blacklist, scheduling
>          Time Spent: 15h 10m
>  Remaining Estimate: 0h
>
> My company has gone through a fault in production, in which a critical switch causes unstable network for a set of machines with package loss rate of 30%-50%. In such fault, the supervisors and workers on the machines are not definitely dead, which is easy to handle. Instead they are still alive but very unstable. They lost heartbeat to the nimbus occasionally. The nimbus, in such circumstance, will still assign jobs to these machines, but will soon find them invalid again, result in a very slow convergence to stable status.
> To deal with such unstable cases, we intend to implement a blacklist scheduler, which will add the unstable nodes (supervisors, slots) to the blacklist temporarily, and resume them later. 



--
This message was sent by Atlassian JIRA
(v6.4.14#64029)