Github user jerryshao commented on the issue: https://github.com/apache/spark/pull/18683 Did you see an explicit performance change while changing this parameter? I would think netty client thread number for shuffle is still a bottleneck even if you split into more fetch requests. We already have bunch of configurations to control the request size, memory usage, bytes in flight here in shuffle fetch, adding more configuration really complex the logics.
--- If your project is set up for it, you can reply to this email and have your reply appear on GitHub as well. If your project does not have this feature enabled and wishes so, or if the feature is enabled but not working, please contact infrastructure at infrastruct...@apache.org or file a JIRA ticket with INFRA. --- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org