You are viewing a plain text version of this content. The canonical link for it is here.

Posted to issues@flink.apache.org by "Yingjie Cao (Jira)" <ji...@apache.org> on 2022/07/29 12:00:00 UTC

[jira] [Resolved] (FLINK-28519) Fix the bug that SortMergeResultPartitionReadScheduler may not read data sequentially

     [ https://issues.apache.org/jira/browse/FLINK-28519?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]

Yingjie Cao resolved FLINK-28519.
---------------------------------
    Resolution: Fixed

Merged into master via f88489a6af42638679429df3fdb4818c278cacbf

> Fix the bug that SortMergeResultPartitionReadScheduler may not read data sequentially
> -------------------------------------------------------------------------------------
>
>                 Key: FLINK-28519
>                 URL: https://issues.apache.org/jira/browse/FLINK-28519
>             Project: Flink
>          Issue Type: Sub-task
>          Components: Runtime / Network
>            Reporter: Yingjie Cao
>            Assignee: Yuxin Tan
>            Priority: Major
>              Labels: pull-request-available
>             Fix For: 1.16.0
>
>
> Currently, the SortMergeResultPartitionReadScheduler always gets all active subpartition readers and read at most one data region for them. It is common that some subpartitions are requested before others and their region indexes are ahead of others. If all region data of a subpartition can be read in one round, some subpartition readers will always ahead of others which will cause random IO. This patch fixes this case by polling one subpartition reader at a time.



--
This message was sent by Atlassian Jira
(v8.20.10#820010)