A bit old, but thought that in the light of latest posts about MapReduce and Hadoop future, it made sense to have this piece of the puzzle too.
Tasso Argyros (AsterData):
Native MapReduce execution is not fundamentally slow; however Google’s MapReduce and Hadoop happen to be oriented more towards batch processing. Dremel tries to overcome that by building a completely different system that speeds interactive querying.
The Dremel: Interactive Analysis of Web-Scale Datasets paper can be downloaded from ☞ here (PDF).
Original title and link: Google’s Dremel: Can MapReduce Handle Fast, Interactive Querying? (NoSQL databases © myNoSQL)