[
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)
