diff options
Diffstat (limited to 'docs/tuning.md')
| -rw-r--r-- | docs/tuning.md | 5 |
1 files changed, 3 insertions, 2 deletions
diff --git a/docs/tuning.md b/docs/tuning.md index f491ae9b95..a4be188169 100644 --- a/docs/tuning.md +++ b/docs/tuning.md @@ -39,7 +39,8 @@ in your operations) and performance. It provides two serialization libraries: for best performance. You can switch to using Kryo by calling `System.setProperty("spark.serializer", "org.apache.spark.serializer.KryoSerializer")` -*before* creating your SparkContext. The only reason it is not the default is because of the custom +*before* creating your SparkContext. This setting configures the serializer used for not only shuffling data between worker +nodes but also when serializing RDDs to disk. The only reason Kryo is not the default is because of the custom registration requirement, but we recommend trying it in any network-intensive application. Finally, to register your classes with Kryo, create a public class that extends @@ -67,7 +68,7 @@ The [Kryo documentation](http://code.google.com/p/kryo/) describes more advanced registration options, such as adding custom serialization code. If your objects are large, you may also need to increase the `spark.kryoserializer.buffer.mb` -system property. The default is 32, but this value needs to be large enough to hold the *largest* +system property. The default is 2, but this value needs to be large enough to hold the *largest* object you will serialize. Finally, if you don't register your classes, Kryo will still work, but it will have to store the |