[ https://issues.apache.org/jira/browse/FLINK-25200?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17478674#comment-17478674 ]
Yun Tang commented on FLINK-25200: ---------------------------------- For general RocksDB incremental checkpoint, we should also test uploading 64MB files V.S copying 64MB file as RocksDB has the default 64MB SST files. Moreoever, I noticed that the write throughput can be reached to 100MB/s, from my understanding, this behavior looks really good on cloud environment. Do you ensure that the test logic is reading local files and then write to remote S3 instead of directly write to remote S3? > Implement duplicating for s3 filesystem > --------------------------------------- > > Key: FLINK-25200 > URL: https://issues.apache.org/jira/browse/FLINK-25200 > Project: Flink > Issue Type: Sub-task > Components: FileSystems > Reporter: Dawid Wysakowicz > Priority: Major > Fix For: 1.15.0 > > > We can use https://docs.aws.amazon.com/AmazonS3/latest/API/API_CopyObject.html -- This message was sent by Atlassian Jira (v8.20.1#820001)