parthchandra opened a new pull request, #126: URL: https://github.com/apache/arrow-datafusion-comet/pull/126
## Which issue does this PR close? Closes #124 ## Rationale for this change The current parallel reader implementation opens and closes too many connections to the file system. This can be reduced by using a fixed number of connections which does not exceed the number of threads used by the parallel reader ## What changes are included in this PR? Creates read ranges and assigns consecutive read range to each thread which then opens only one connection to read the ranges it has been assigned. ## How are these changes tested? TPC-DS benchmark queries on AWS/S3. -- 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]
