om 1000 to 100. Now I can run
> distinct and reduceByKey on files that are 2G / 50M lines.
>
> Unfortunately it still doesn't scale well.
>
> Thanks.
>
>
>
> --
> View this message in context:
> http://apache-spark-user-list.1001560.n3.nabble.com/Exception-in
number of splits from 1000 to 100. Now I can run
distinct and reduceByKey on files that are 2G / 50M lines.
Unfortunately it still doesn't scale well.
Thanks.
--
View this message in context:
http://apache-spark-user-list.1001560.n3.nabble.com/Exception-in-connection-from-worker-to-w