Harvard Tackles Storage Issues

The Life Sciences program is comprised of many interdisciplinary research areas, including departments in chemistry and biology. While every research community has a unique focus and specific projects of interest, there is a great deal of cross-departmental collaboration and shared initiatives among our thousands of researchers and scientists. A vital technology priority among the various Life Sciences areas is the need for fast and efficient data storage.

The Technology Dilemma

Steadily increasing research data requirements within the Life Sciences mandated a better mass-storage system, one beyond the traditional, limited direct-attached storage and network-attached storage (NAS) options used by many research departments.

Our existing storage systems were not scalable; there was a limited quantity of storage available to each server and no effective way of centrally managing the proliferation of independent storage solutions. We found that while we could always buy larger drives, we were hitting the manageability and scalability limits of the drives that could be attached.

While there was the option to purchase storage-area network (SAN) capability through Harvard’s central IT services, the cost was deemed prohibitive and the available capacity wouldn’t meet our future storage needs.

Any new data storage solution would first have to interact seamlessly with the Life Sciences’ heterogeneous client environments. In addition, we had three specific criteria for our storage needs: scalability, performance, and cost. We also wanted flexibility, the capability to have both fast Fibre Channel and slower, less-expensive ATA storage managed together. We needed a vendor whose system could scale as high as possible, because we don’t know how many users would be involved in our community’s future.

Harvard Life Sciences ultimately determined that building a SAN fabric was too expensive, both standalone NAS and direct-attached storage were far too limited, and that a hybrid NAS-on-SAN approach would give the most flexibility and scalability for considerably less cost.

We chose the BlueArc Titan SiliconServer, a modular network storage system that can fetch and retrieve data from disk arrays at extremely high speed and manage the data loads under a single file system. Titan can handle 256 trillion bytes of information. Its special programmable architecture transfers data to drives at 5Gbps, and BlueArc is aiming to hike that speed to 20Gbps in the near future.

Titan’s hardware-based Silicon File System uses virtual volumes to partition data for users, groups or departments—allowing storage administrators to dynamically expand and contract storage allocations to meet individual needs. This eliminates downtime that many other systems require due to data migration and reallocation.

With our new Titan systems, Harvard Life Sciences already has 28 terabytes of mixed Fibre Channel and ATA storage, all managed together. We are poised for quick growth and can use our storage solution for a wide range of needs—from traditional file and database services to replacing old, expensive tape backup solutions, even as a fail-safe mechanism for disaster recovery at an off-site location.

Future storage needs are no longer a worry, as Titan allows Harvard Life Sciences to grow our mass-storage solution without requiring purchase of additional controllers—a key differentiator from other vendor options.

Our community will benefit from Titan’s modular blade architecture that provides investment protection—including upgrades to new technologies like 10Gb Ethernet. In addition to its technical capabilities, the BlueArc system will eventually save the Life Sciences Program millions of dollars, as our teams will be able to consolidate our hundreds of terabytes of direct-attached storage spread across thousands of servers.

Cost savings also filter down to our user base, because users no longer need to buy their own individual, limited, backup or mass-storage solutions. This is basically a shared resource among all of our researchers.

We expect that the Titan product will provide a fourfold increase over our current performance metrics and that performance will only increase as we upgrade our Ethernet networks to support 10GB capabilities. We’ve been extremely pleased with our choice and the solution that BlueArc has been able to provide.

Featured

  • artificial intelligence on laptop

    OpenAI to Combine AI Products into Desktop 'Superapp'

    OpenAI is reportedly developing a desktop application that would combine several of its emerging AI products into a single platform, according to reports, marking the latest step in the company's effort to transform ChatGPT from a standalone chatbot into a broader productivity and automation environment.

  • woman surrounded by virtual hologram icons

    Beyond AI Adoption: Designing Learning for an Age of Abundant Intelligence

    Higher education was designed for a world in which access to knowledge, expertise, feedback, mentorship, and authentic learning experiences were inherently scarce. By making many forms of intelligence increasingly abundant, AI is inherently redefining the existing paradigm.

  • digital brain with network connections

    Microsoft Moving to Internally Developed AI Models in Office Apps

    Microsoft is reportedly using its own in-house artificial intelligence models to handle some workloads in Excel and Outlook, offering new evidence that the company is moving its AI strategy beyond model development and into large-scale cost reduction.

  • Profile silhouette of a person thoughtfully touching their chin, overlaid with transparent data visualizations and digital interface elements suggesting artificial intelligence and analytics.

    The Institutional Knowledge Shift Is Reshaping Higher Ed IT

    Higher education IT leaders are navigating a quiet but consequential transition: Experienced team members are retiring or leaving for private-sector roles, and the teams replacing them are smaller, newer, and often stretched thin. The result is a structural shift in how technology decisions are made, executed, and sustained.