spark-user mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From sranga <sra...@gmail.com>
Subject RDD Cache Cleanup
Date Tue, 25 Nov 2014 17:54:58 GMT
Hi

I am noticing that the RDDs that are persisted get cleaned up very quickly.
This usually happens in a matter of a few minutes. I tried setting a value
of 20 hours for the /spark.cleaner.ttl/ property and still get the same
behavior.
In my use-case, I have to persist about 20 RDDs each of size 10 GB. There is
enough memory available (around 1 TB). The /spark.storage.memoryFraction/
property is set at 0.7. 
How does the cleanup work? Any help is appreciated.


- Ranga



--
View this message in context: http://apache-spark-user-list.1001560.n3.nabble.com/RDD-Cache-Cleanup-tp19771.html
Sent from the Apache Spark User List mailing list archive at Nabble.com.

---------------------------------------------------------------------
To unsubscribe, e-mail: user-unsubscribe@spark.apache.org
For additional commands, e-mail: user-help@spark.apache.org


Mime
View raw message