Blazent’s big data processing engine is at the core of our ability to handle all your IT data, no matter the volume, complexity or velocity. The engine sits at the intersection of all Blazent’s aligned and validated data across a large swath of the IT world, providing insight into what’s happening, who’s involved, what’s working as it should, and where more attention should be focused.
The engine works with all the disparate data sources it encounters, then stores every representation of every entity of every source of all that data, across time. No other data engine has this versatility or capability.
Our engine is hosted in cloud environments including Amazon Web Services (AWS) in North America and Europe and the Verizon Terramark secure cloud infrastructure. To optimize flexibility, the Blazent architecture incorporates a number of leading open-source tools, including Hadoop software framework for distributed storage and processing and Cassandra DBMS. It utilizes the Redis key-pair value dictionary to recognize prior uses or changes.
Messaging from the various nodes of the cluster is via the Apache ActiveMQ message broker. It also employs the Spark query engine, the leading query engine for NoSQL databases and Spark’s scalable MLlib (Machine Learning Library) of common learning algorithms and utilities.
Blazent uses HDFS (Hadoop Distributed File System) to store its massive datasets. Hadoop and the HDFS structure enable long-term history of all the data the Blazent engine processes, enabling enterprises to draw from the accumulated data and knowledge and to use this data for future analysis.
To learn more, read our White Paper