Mailing-List: contact issues-help@flink.apache.org; run by ezmlm
Precedence: bulk
Reply-To: dev@flink.apache.org
Date: Mon, 19 Dec 2016 13:02:59 +0000 (UTC)
From: "Fabian Hueske (JIRA)" <jira@apache.org>
To: issues@flink.apache.org
Message-ID: <JIRA.13028300.1481781497000.552906.1482152579156@Atlassian.JIRA>
In-Reply-To: <JIRA.13028300.1481781497000@Atlassian.JIRA>
References: <JIRA.13028300.1481781497000@Atlassian.JIRA> <JIRA.13028300.1481781497101@arcas>
Subject: [jira] [Commented] (FLINK-5342) Setting the parallelism
 automatically for operators base on cost model
MIME-Version: 1.0
Content-Type: text/plain; charset=utf-8
Content-Transfer-Encoding: 7bit
archived-at: Mon, 19 Dec 2016 13:03:01 -0000


    [ https://issues.apache.org/jira/browse/FLINK-5342?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15761106#comment-15761106 ] 

Fabian Hueske commented on FLINK-5342:
--------------------------------------

Yes, I think the {{TableConfig}} would be a good place to add such a parameter. However, this does not give very fine-grained control, because all joins or aggregations would be executed with the same parallelism. Chaining of map-based operator should not be a problem. Another interesting parameter could be the parallelism of the final result.

> Setting the parallelism automatically for operators base on cost model
> ----------------------------------------------------------------------
>
>                 Key: FLINK-5342
>                 URL: https://issues.apache.org/jira/browse/FLINK-5342
>             Project: Flink
>          Issue Type: Improvement
>          Components: Table API & SQL
>            Reporter: godfrey he
>
> On Flink table API, a query will be translated to operators without parallelism. And user do not know even do not care the target operators translated from query. So it's better to set the parallelism automatically for each operator base on cost model.


--
This message was sent by Atlassian JIRA
(v6.3.4#6332)