Github user tgravescs commented on the pull request:
https://github.com/apache/spark/pull/3525#issuecomment-65132142
Basically I would like some hard data or user input before changing this
since changing/adding configs can just lead to more confusion. I have seen a
few cases where a % wasn't ideal. I've seen others where 7% worked just fine.
Overall I'd like to understand if % covers the majority of cases or if say it
is only useful doing etl but then breaks down doing ML or graphx. We had this
discussion briefly before and left it at the value vs % and I haven't really
seen much more data to change it but perhaps others have?
---
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]
