You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@flink.apache.org by "ASF GitHub Bot (JIRA)" <ji...@apache.org> on 2019/07/10 20:20:00 UTC

[jira] [Updated] (FLINK-13187) Expose batch slot request via new scheduling mode

     [ https://issues.apache.org/jira/browse/FLINK-13187?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]

ASF GitHub Bot updated FLINK-13187:
-----------------------------------
    Labels: pull-request-available  (was: )

> Expose batch slot request via new scheduling mode
> -------------------------------------------------
>
>                 Key: FLINK-13187
>                 URL: https://issues.apache.org/jira/browse/FLINK-13187
>             Project: Flink
>          Issue Type: Sub-task
>          Components: Runtime / Coordination
>    Affects Versions: 1.9.0
>            Reporter: Till Rohrmann
>            Assignee: Till Rohrmann
>            Priority: Major
>              Labels: pull-request-available
>             Fix For: 1.9.0
>
>
> In order to leverage the newly introduced batch slot request feature introduced with FLINK-13166, we should introduce a new {{ScheduleMode#LAZY_FROM_SOURCES_WITH_BATCH_SLOT_REQUESTS}}. Users who enable this, must make sure that the generated job does not contain any pipelined shuffles because this can lead to resource deadlocks (not timing out requests with too few slots to make a pipelined region run). 



--
This message was sent by Atlassian JIRA
(v7.6.3#76005)