Github user bien commented on the pull request:
https://github.com/apache/spark/pull/5351#issuecomment-90653352
It is a very large dataset: I was training on 30M instances x 500 features
at tree max depth 17. I had to adjust strategy.maxMemoryInMB,
--executor-memory, and -Xmn upwards in order to get decent throughput.
In the commit you'll see that I converted NodeIdCache.scala away from
MEMORY_ONLY.
---
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 [email protected] or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
