BestPeer’s flagship product is the BestPeer++ Platform, which combines the powerful MapReduce processing model with the conventional P2P database technologies. By incorporating the MapRecude runtime of Apache Hadoop with database execution engine, BestPeer++ allows flexible and efficient processing of massive data sets.



BestPeer++’s advanced technology features a hybrid architecture that brings the parellelism of MapReduce to the latest development in relational database research. RDBMS technology has developed significantly over the past several decades, but current analytic solutions were designed prior to the advent of Hadoop and the paradigm shift from appliance-based computing to distributed computing on clusters of inexpensive commodity hardware. BestPeer++ is based on our decade's research on P2P database system, and offers an accelerated data processing engine and a more flexible portability via the adoption of MapReduce framework and Software-as-a-Service(SaaS) paradigm.


In contrast to the “Hadoop Connector” strategy employed by many MPP analytic database vendors, BestPeer++ uses Hadoop as the parallelization layer to facilitate its global query processing, with each node running a database instance. Consolidating conventional database query processing and MapReduce into a single platform drastically reduces TCO, eliminates performance bottleneck from both mechanism, and allows for richer analytics through consumption of diverse data types. Additionally, BestPeer++’s unified architecture and flexible schema capabilities reduce the complexities associated with emerging analytic use cases – including graph analysis, clustering, and classification – while dramatically increasing performance and scale.

Specifically, highlights of BestPeer++ are:

  • Amazon Cloud Adapter: The key idea of BestPeer++ is to use dedicated database servers to store data for each business and organize those database servers through P2P network for data sharing. The Amazon Cloud Adapter provides an elastic hardware infrastructure for BestPeer++ to operate on by using Amazon Cloud services.
  • The BestPeer++ Core: The BestPeer++ core contains all platform-independent logic, including query processing and P2P overlay. It runs on top of adapter and consists of two software components: bootstrap peer and normal peer.
  • Adaptive Query Processor: BestPeer++ employs a hybrid design for achieving high performance query processing. The major workload of a corporate network is simple, low-overhead queries. Such queries typically only involve querying a very small number of business partners and can be processed in short time. BestPeer++ is mainly optimized for these queries. For infrequent time-consuming analytical tasks, we provide an interface for exporting the data from BestPeer++ to Hadoop and allow users to analyze those data using MapReduce.