Databases Reference
In-Depth Information
“NetApp AutoSupport data is extremely valuable to us,” said Marty Mayer, director of NetApp
AutoSupport. “Our customers depend on us to utilize the data to respond in a timely manner
when potential problems and issues arise. Additionally, we actively analyze customer storage sys-
tem data for fitness and health checks that help optimize the investment our customers have made in
NetApp.”
The solution: netapp open solution for hadoop
The team focused on storage solutions that support the Apache Hadoop open-source software
designed for data-intensive distributed applications. Other criteria included scalability, high-per-
formance, and rich analytics capabilities. The AutoSupport group conducted a proof of concept on
numerous technologies, evaluating them for key functions, including parsing, ETL capabilities, and
data warehousing. The team concluded that the NetApp Open Solution for Hadoop—comprised of
NetApp storage coupled with Cloudera Enterprise—surpassed the other solutions in providing the
ability to more deeply monitor customer solutions, and executing previously impossible data process-
ing jobs and complex queries. The solution also provided an overall lower total cost of ownership
than other Big Data platforms.
NetApp and Cloudera joined forces to offer organizations a solution that is highly scalable with
enterprise storage features that improve reliability and performance and reduce costs. NetApp Open
Solution for Hadoop customers can leverage the Big Data platform to accelerate adoption of analytic
applications that deliver real-time results across intense data and computational workloads. Cloudera
is a major enabler for the enterprise adoption and production use of Apache Hadoop. Cloudera
Enterprise allows companies to manage the complete operational life cycle of their Apache Hadoop
systems with deep visibility into their CDH clusters. It also automates the ongoing system changes
needed to maintain and improve the quality of operations.
System architecture
The NetApp AutoSupport team deployed NetApp Open Solution for Hadoop, which includes a
28-node cluster of Cloudera Enterprise on four NetApp E2600 storage systems and a NetApp
FAS2040 system. Mayer noted,
The NetApp Open Solution for Hadoop system offers us the scalability and flexibility we need to effec-
tively support our growing client base and rapidly expanding data stores. In addition, because the
NetApp system addresses our parsing, ETL, and data warehousing needs in a single, comprehensive
solution, it reduces our total cost of ownership, freeing up budget for other customer-focused projects.
The system offers high availability and high performance for even the most demanding
AutoSupport workloads. Its balanced performance will sustain the high read and write through-
put requirements of the system's data-intensive, high-bandwidth applications, such as the weekend
reporting that offers visibility into the health of hundreds of thousands of customer storage systems.
As a customer-facing organization, the NetApp AutoSupport team depends on the reliability of its
storage environment 24/7/365. Data ONTAP® 8 on the FAS2040 storage system eliminates the single
