Reynold Xin created SPARK-17949:

             Summary: Introduce a JVM object based aggregate operator
                 Key: SPARK-17949
             Project: Spark
          Issue Type: Improvement
          Components: SQL
            Reporter: Reynold Xin

The new Tungsten execution engine has very robust memory management and speed 
for simple data types. It does, however, suffer from the following:

1. For user defined aggregates (Hive UDAFs, Dataset typed operators), it is 
fairly expensive to fit into the Tungsten internal format.

2. For aggregate functions that require complex intermediate data structures, 
Unsafe (on raw bytes) is not a good programming abstraction due to the lack of 

The idea here is to introduce an JVM object based hash aggregate operator that 
can support the aforementioned use cases. This operator, however, should limit 
its memory usage to avoid putting too much pressure on GC, e.g. falling back to 
sort-based aggregate as soon the number of objects exceed a very low threshold.

Internally at Databricks we prototyped a version of this for a customer POC and 
have observed substantial speed-ups over existing Spark.

This message was sent by Atlassian JIRA

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

Reply via email to