[jira] [Created] (FLINK-10461) Speed up download file procedure when restore

[Shang Yuanchun (Jira)]

Congxian Qiu created FLINK-10461:
------------------------------------

             Summary: Speed up download file procedure when restore
                 Key: FLINK-10461
                 URL: https://issues.apache.org/jira/browse/FLINK-10461
             Project: Flink
          Issue Type: Improvement
          Components: State Backends, Checkpointing
            Reporter: Congxian Qiu


In the current master branch, the restore will download file from DFS, the download procedure are single-thread, this could speed up by using multi-thread for downloading states from DFS.

 

In my company, the states will come to some terabytes, so the restore procedure will become a litter slow, after a bit digging, I find download states from DFS using single thread, this could using multi-thread for speed up.

I test the time used for download states from DFS with ~2 terabytes states. With single thread it used 640+s, and 130+s when using 5 threads for download.



--
This message was sent by Atlassian JIRA
(v7.6.3#76005)