My clients at Teradata are introducing a mix-em/match-em Aster/Hadoop box, officially called the Teradata Aster Big Analytics Appliance. Basics include:
- You can fill a rack with nodes either for the Aster DBMS or for Hadoop (Hortonworks flavor), or you can combine them in the same box.
- If you combine them, they share management software (adapted from mainstream Teradata’s) and Infiniband.
- An Aster node has 16 2.6-gigahertz cores and 24 900GB disk drives.
- A Hadoop node has 12 2.0-gigahertz cores and 12 3TB drives.
- A central part of Teradata’s strategy is that Aster and Hadoop nodes can work together via SQL-H.
- The Teradata Aster Big Analytics Appliance is based on a family of Dell servers that fit more compactly into racks than do Teradata’s traditional products.
- The Teradata Aster Big Analytics Appliance replaces a previous interim Teradata Aster appliance that used similar hardware to that in other Teradata systems.
My views on the Teradata Aster Big Analytics Appliance start:
- From an Aster standpoint — why not?
- Overall, I’m not a big fan of Hadoop appliances. It’s not always obvious how appliance packaging adds enough value to make up for sacrifices in cost and flexibility.
- One exception would be if the appliance comes with some software you want and can’t get in another way. So if you’re happy with Teradata’s management software, and they give you a good enough price — why not?
- The Aster/Hadoop arm’s-length integration strategy indeed calls for a high-speed interconnect between the two.
- If you’re going to a roll your own Hadoop cluster, Teradata’s design choices might be a good starting point for you.
- I don’t dislike the term “big analytics” nearly as much as I do the term “big data“.
- I took the opportunity to chat with Teradata hardware chief Carson Schmidt, in part about the rationale for these design choices.
- You might want to compare the hardware specs for the Teradata Aster Big Analytics Appliance to those for four different Teradata systems (March, 2012)
- Edit: Timothy Prickett Morgan picked up a nuance I missed: Aster’s backup and load nodes are on cheaper, Hadoop-style configurations.