Editor’s Note: Welcome to our weekly Reader Forum section. In an attempt to broaden our interaction with our readers we have created this forum for those with something meaningful to say to the wireless industry. We want to keep this as open as possible, but we maintain some editorial control to keep it free of commercials or attacks. Please send along submissions for this section to our editors at: [email protected].
The rise of cloud computing has led telecommunication service providers to examine their “big data” storage infrastructure with a renewed focus on improving performance and reducing costs. Scaling and improving performance in a cost-effective manner is the top priority.
To address these challenges, many data centers are migrating toward centralizing data in a single location and making it accessible via the Internet from anywhere in the world. On first blush, this makes sense. Centralizing storage equipment keeps costs down. Improved Internet connections, better performance and reliability are additional benefits of a single, large data center. Yet with these improvements in performance, scalability is made more difficult and expensive. Improvements require purchasing high-performance, specialized equipment, which increases costs and energy consumption. Faced with these challenges, telcos are looking for a smarter way to scale.
Cloud performance
Performance problems, like data bottlenecks, are a big concern for TSPs, which manage far more users and greater performance demands than do enterprises. While the average user of an enterprise system demands high performance, these users are typically accessing, sending and saving reasonably low-volume files like documents and spreadsheets, resulting in lower storage use and lightening the performance load.
Users of TSP services, however, are a different story. When the TSP system is being accessed simultaneously over the Internet by a high volume of users, it results in a performance bottleneck. Telco storage systems not only have to scale to each additional user, but must also maintain the same level of performance across the network.
Significantly, the average TSP user is accessing and storing far larger files – music, photo and video files – than the average enterprise user does.
Best practices for scaling storage
The business implications for TSPs are profound. They must be able to scale quickly to accommodate the increasing demand for data storage. Consumers are used to free online storage, and are not shy about ditching providers that start charging for services. To be cost-effective, TSPs need extremely cheap storage that scales easily and performs well.
Three best practices for TSPs seeking an ideal combination of performance, scalability and cost-effectiveness include:
–Utilize commodity components: Low-energy hardware makes good business sense. Commodity-component servers not only cost less, but they also use far less energy, which significantly reduces both setup and operating costs in one move.
–Scale smarter with distributed storage: Even though the data center trend has been moving toward centralization, distributed storage presents the best way to build at scale. This is because there are now ways to improve performance at the software level that neutralize the performance advantage of a centralized data storage approach.
–Avoid a single point of entry: A single point of entry can become a single point of failure, especially with the demands of consumers on big data storage. Also, a single point of entry becomes a performance bottleneck very easily. Adding caches to alleviate the bottleneck, as most TSPs presently do, adds cost and complexity to a system very quickly. On the other hand, a horizontally-scalable system that distributes data among all nodes provides superior redundancy.
Conclusion
High-performance, vertically-scaled storage systems are the focal points of the big data storage landscape today. Since these current architectures can often only scale to a single petabyte and are expensive, they are not as cost-effective or sustainable in the long run. Migrating to a horizontally-scaled data storage model that allocates data evenly onto low-energy hardware can decrease costs and expand performance in the cloud. These best practices can lead TSPs to improve the scalability, performance and efficiency of their data storage centers, increasing consumer loyalty and generating immediate return on investment.
