Rajesh Balamohan created HDDS-3703:
--------------------------------------
Summary: Consider avoiding file lookup calls in writeChunk hotpath
Key: HDDS-3703
URL: https://issues.apache.org/jira/browse/HDDS-3703
Project: Hadoop Distributed Data Store
Issue Type: Improvement
Reporter: Rajesh Balamohan
Attachments: Screenshot 2020-06-02 at 5.28.59 PM.png
In getChunkFile internally, it invokes "verifyChunkDirExists". This causes file
existence checks for the directory and throws IO exception accordingly. If the
file is anyways going to be written, it is better to handle it later and throw
the same exception. This could avoid file checks for every "writechunk"
[https://github.com/apache/hadoop-ozone/blob/master/hadoop-hdds/container-service/src/main/java/org/apache/hadoop/ozone/container/keyvalue/impl/FilePerBlockStrategy.java#L106]
File channels are cached anyways in "OpenFiles". So if we can avoid
"file.getAbsolutePath()", this could save memory and resolving paths.
[https://github.com/apache/hadoop-ozone/blob/master/hadoop-hdds/container-service/src/main/java/org/apache/hadoop/ozone/container/keyvalue/impl/FilePerBlockStrategy.java#L118]
Also "validateChunkForOverwrite" can be optimised, as "isOverWritePermitted"
would be false most of the times.
!Screenshot 2020-06-02 at 5.28.59 PM.png|width=835,height=510!
--
This message was sent by Atlassian Jira
(v8.3.4#803005)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
