SnappyData fuses Apache Spark with an in-memory database to deliver a data engine capable of stream processing, transactions and interactive analytics in a single cluster.
The SnappyData Approach. In-memory database fused into Spark
SnappyData fuses a low latency, highly available in-memory database into Spark with shared memory management and several optimizations. The net effect is an order of magnitude performance improvement even compared to native spark caching and more than 2 orders of magnitude performance benefit compared to working with external data sources.
Discover more about our approach
Interactive Analytics @ scale
Reduced latency through data colocation, code generation & vectorization
Support multiple data formats
Data format agnostic: Support for structured and semi-structured data
Transactional and analytical processing in one platform. Lower your complexity.
SnappyData bridges the OLTP/OLAP gap in data management by offering support for both transactional and analytic workloads. SnappyData supports both row and column tables in the store. The catalyst engine in Spark has been extended to be more data aware thereby offering higher performance. A single application running on SnappyData can invoke OLTP & OLAP queries in streaming or batch contexts.
Row and Column Tables
Optimized for very fast writes, fast key/index based lookups and more
Our optimized data co-location techniques minimize JOIN shuffling
Discover more about the Platform
Flexible and compatible with the Spark Ecosystem. Use the right options for you.
SnappyData is 100% compatible with Spark which means your Spark programs will run unchanged in SnappyData. Applications access the data store using JDBC/ODBC/REST or simply use the enhanced Spark API using Scala, Java, and Python.
Discover more about SnappyData's APIs
Utilize the most well known query language to build applications on SnappyData. JDBC & OBDC APIs provided.
Any Spark application can access SnappyData by a simple extension of the SparkContext.
SnappyData’s Synopses Data Engine (SDE). Interactive query latency always.
Databases are often incapable of delivering truly interactive analytics, when faced with large data volumes or high velocity streams. SnappyData’s Synopsis Data Engine combines state-of-the-art approximate query processing techniques and a variety of data synopses to ensure interactive analytics over both streaming and stored data. Through a novel concept of high-level accuracy contracts (HAC), SnappyData is the first to offer end users an intuitive means for expressing their accuracy requirements without overwhelming them with statistical concepts.
Continue increasing data volumes and maintain constant latency in the sub-millisecond range
Lower Memory Footprint
Reduce the memory required for storage by orders of magnitude.