You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@flink.apache.org by "Stephan Ewen (Jira)" <ji...@apache.org> on 2020/11/05 15:06:00 UTC
[jira] [Resolved] (FLINK-19597) Introduce SortBuffer and
PartitionSortedBuffer for sort-merge based blocking shuffle
[ https://issues.apache.org/jira/browse/FLINK-19597?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Stephan Ewen resolved FLINK-19597.
----------------------------------
Assignee: Yingjie Cao
Resolution: Fixed
Implemented in 1.12.0 (master) via 7ea1168efa70470602f735a8c2d81ccf7aa14ba7
> Introduce SortBuffer and PartitionSortedBuffer for sort-merge based blocking shuffle
> ------------------------------------------------------------------------------------
>
> Key: FLINK-19597
> URL: https://issues.apache.org/jira/browse/FLINK-19597
> Project: Flink
> Issue Type: Sub-task
> Components: Runtime / Network
> Affects Versions: 1.12.0
> Reporter: Yingjie Cao
> Assignee: Yingjie Cao
> Priority: Major
> Fix For: 1.12.0
>
>
> Data of different channels can be appended to a SortBuffer and after the SortBuffer is finished, the appended data can be copied from it in channel index order. PartitionSortedBuffer is an implementation of SortBuffer and it sorts all appended records only by subpartition index. Records of the same subpartition keep the appended order.
--
This message was sent by Atlassian Jira
(v8.3.4#803005)