spark-user mailing list archives

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

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
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 /
property is set at 0.7. 
How does the cleanup work? Any help is appreciated.

- Ranga

View this message in context:
Sent from the Apache Spark User List mailing list archive at

To unsubscribe, e-mail:
For additional commands, e-mail:

View raw message