Github user ankurdave commented on the pull request: https://github.com/apache/spark/pull/497#issuecomment-42397518 Thanks for the comments! I implemented your suggestions as well as some cleanups I'd discussed with @rxin, then benchmarked it on 16 m2.4xlarge machines with the uk-2007-05 web graph for 10 iterations of PageRank to make sure it didn't introduce a performance regression. Commit | Runtime +/- SEM --- | --- pre-unify-rdds (f96ea3a02f64e6e0fec4dcb1f498c6bcde4af699) | 418 +/- 17.1 s unify-rdds (57202e81cc89056d86d9d9de18173b7553300a97) | 390.5 +/- 13.9 s
--- 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. ---