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

Posted to issues@ozone.apache.org by "Attila Doroszlai (Jira)" <ji...@apache.org> on 2019/12/12 08:44:00 UTC

[jira] [Created] (HDDS-2713) Decouple client write size and datanode chunk size

Attila Doroszlai created HDDS-2713:
--------------------------------------

             Summary: Decouple client write size and datanode chunk size
                 Key: HDDS-2713
                 URL: https://issues.apache.org/jira/browse/HDDS-2713
             Project: Hadoop Distributed Data Store
          Issue Type: Improvement
          Components: Ozone Datanode, SCM Client
            Reporter: Attila Doroszlai
            Assignee: Attila Doroszlai


Currently Datanode creates chunk files as they are received from HDDS client.  This creates a conflict between requirements: client would like to use less memory for buffering, but datanode needs to avoid small files.

The goal of this task is to decouple client and server write sizes to allow the client to send data in smaller increments without affecting datanode storage.



--
This message was sent by Atlassian Jira
(v8.3.4#803005)

---------------------------------------------------------------------
To unsubscribe, e-mail: ozone-issues-unsubscribe@hadoop.apache.org
For additional commands, e-mail: ozone-issues-help@hadoop.apache.org