Jan 7, 2015

SQL for big data: Price-performance advantages of bare metal

Ansley Kilgore

SQL for big dataWhen building your big data infrastructure, price performance is a critical factor to evaluate. Data-intensive workloads with the capacity to rapidly scale to hundreds of servers can escalate costs beyond your expectations. The inevitable growth of the Internet of Things (IoT) and fast big data will only lead to larger datasets, and a high-performance infrastructure and database platform will be essential to extracting business value while keeping costs under control.

Benchmarking SQL on bare metal vs. virtual cloud

Performance metrics should be evaluated in terms of overall cost. To demonstrate this, Internap and ParStream have conducted benchmark tests comparing ParStream real-time analytics SQL databases on bare metal and virtualized public cloud. While the latest SQL databases have been created specifically for cloud, there are significant performance advantages of running these databases on bare metal.

Certain industries, such as advertising technology and online data analytics, require ultra-low latency in order to extract, analyze and process large amounts of data in real time. Because of this requirement, query response time is a vital metric for this type of big data infrastructure. Benchmark tests confirm that running the ParStream SQL database on Internap’s bare metal Infrastructure-as-a-Service (IaaS) delivered substantial benefits when compared to AWS EC2.

Price-performance advantages

Bare-metal cloud offers a high-performance, cost-efficient alternative to virtual cloud solutions. While many data-intensive applications begin in virtual cloud environments, increased volatility and inconsistent performance can become problematic as the business expands and scales. Bare metal offers organizations the flexibility and control of the cloud without the “noisy neighbor” problem inherent in multi-tenant virtual cloud environments. The dedicated CPU, RAM and disk I/O of bare metal IaaS provide a cost-effective way to achieve the high-performance requirements of big data infrastructure.

Download the Performance Analysis Report to see complete benchmark test results and learn more about the advantages of running SQL databases on bare metal for big data and IoT workloads.

Explore HorizonIQ
Bare Metal


About Author

Ansley Kilgore

Read More