[
https://issues.apache.org/jira/browse/HAWQ-234?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15047484#comment-15047484
]
C.J. Jameson commented on HAWQ-234:
-----------------------------------
This looks like it should be many different issues to work on -- can it be
broken down? I see how 1 & 2 go together but it might be easier for all of us
to accept incremental improvements to the algorithm and framework if the others
are separated.
> Improve HAWQ resource manager resource allocation algorithm and RPC framework
> -----------------------------------------------------------------------------
>
> Key: HAWQ-234
> URL: https://issues.apache.org/jira/browse/HAWQ-234
> Project: Apache HAWQ
> Issue Type: Improvement
> Components: Resource Manager
> Reporter: Yi Jin
> Assignee: Yi Jin
>
> 1) reject resource request from dispatcher at once if too many segments
> unavailable;
> 2) explain how many segments unavailable in current cluster when the resource
> request is rejected;
> 3) make error message string generated in resource manager process only for
> all resource manager RPCs;
> 4) change NVSEG_* limits semantic meanings to latest version;
> 5) minimum vseg number for one resource request is changed to queue vseg num
> / active_statements, but the request having only a few vseg required is not
> changed.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
