Carter Shanklin looks at Hive 2’s performance improvements:
LLAP KEY BENEFITS
LLAP enables as fast as sub-second query in Hive by keeping all data and servers running and in-memory all the time, while retaining the ability to scale elastically within a YARN cluster.
LLAP, along with Apache Ranger enables fine-grained security for the Hadoop ecosystem, including data masking and filtering, by providing interfaces for external clients like Spark to read.
LLAP is great for cloud because it caches data in memory and keeps it compressed, overcoming long cloud storage access times and stretching the amount of data you can fit in RAM.
This sounds very much like a response to Spark.