LuciferYang commented on pull request #30663: URL: https://github.com/apache/spark/pull/30663#issuecomment-749047877
It takes 1ms to read parquet footers each time and 0.5ms to read orc tail each time use local ssd , Will use DFS and add some metrics to debug this, there are two `seek + read` operations when read parquet footer, and the second seek is forward seek, the overhead on DFS should be obvious ---------------------------------------------------------------- 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. For queries about this service, please contact Infrastructure at: [email protected] --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
