Business data volumes are growing exponentially with no sign of slowing. Organizations looking to harness value from these “big data” sets in real-time operational settings need the ability to perform analytics quickly and efficiently and advanced data management features such as data protection, recoverability, and cloning. Existing infrastructure and processes that traditionally focused on reporting rather than data mining or analytics are coming up short, reaching plateaus in their ability to scale or meet operational service level agreements.
ParAccel PADB is a high performance, highly scalable analytics platform. Based on a multi-parallel processing (MPP) architecture, it is columnar database software that runs on commodity hardware. Key features such as the compile on query execution, compression on write, and parallel query optimizer turbo-charge extremely complex analytics. The ParAccel PADB and NetApp SAN Optimized solution gives data scientists and line of business owners client access via standard local area network (LAN) connectivity to an MPP database running on commodity servers with SAN integration to NetApp storage.
The functional capabilities of the ParAccel PADB Blended Scan SAN integration option, in combination with NetApp Snapshot and FlexClone technology, were assessed by ESG Lab via hands-on testing at a NetApp facility located in RTP, NC. The reference architecture used commodity servers and ParAccel PADB software configured with the Blended Scan option integrated with NetApp SAN storage. A large data set simulating a real-world operational data store and a TPC-H data model were used.