[
https://issues.apache.org/jira/browse/HADOOP-19647?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=18012895#comment-18012895
]
Steve Loughran commented on HADOOP-19647:
-----------------------------------------
key ones are random, whole file and sequential, with recognising avro, parquet,
a bonus
* parquet does now open files with "parquet" as first entry
* distcp always uses whole-file where a few large 64MB+ blocks deliver great
performance
> ABFS: Read Policy set in openFileOptions should be considered for enabling
> various optimizations
> ------------------------------------------------------------------------------------------------
>
> Key: HADOOP-19647
> URL: https://issues.apache.org/jira/browse/HADOOP-19647
> Project: Hadoop Common
> Issue Type: Sub-task
> Components: fs/azure
> Affects Versions: 3.5.0, 3.4.1
> Reporter: Anuj Modi
> Assignee: Anuj Modi
> Priority: Major
>
> AbfsInputStream should take in account the Read Policy set by user with Open
> File Options. Based on the read policy set, appropriate optimizations should
> be enabled and kicked in.
--
This message was sent by Atlassian Jira
(v8.20.10#820010)
---------------------------------------------------------------------
To unsubscribe, e-mail: common-issues-unsubscr...@hadoop.apache.org
For additional commands, e-mail: common-issues-h...@hadoop.apache.org
