zuston commented on PR #65: URL: https://github.com/apache/incubator-uniffle/pull/65#issuecomment-1192300947
> @zuston From [apache/spark#20119](https://github.com/apache/spark/pull/20119), there has performance issue with NIO's Files API. The performance issue is caused by the default `InputStream.skip` implementation. So i dont replace it in the uniffle `LocalFileReader` class. > I think read data from shuffle server can be improved with solution as zero-copy? After browsing spark related codebase, i think maybe using NIO api of filechannel will improve the performance. But just guess, i have no practice on this and need more test. -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: [email protected] For queries about this service, please contact Infrastructure at: [email protected] --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
