How does FAST™ solve the distributed file storage challenge?

by Jaap van Duijvenbode on May 11, 2015

Thanks to a number of key features, FAST™ combines the best of both worlds, delivering high-performance, secure, simplified solutions for today's distributed enterprise.How does FAST™ solve the distributed file storage challenge?

How does FAST™ solve the distributed file storage challenge?As discussed in our last blog, today's enterprises need to grapple with distributed file storage if they are to remain operational and competitive. Large organizations now regularly employ a tremendous number of workers at disparate locations, from satellite offices to home-based remote personnel. All of these individuals need to be able to access, use and share corporate files easily and quickly. If the company does not have the technology in place to support this level of data access, the organization's productivity will suffer and its end users will become increasingly frustrated. The problem is that two of the leading strategies - centralization and branch office file servers - create their own complications. Specifically, centralization can cause latency and undermine performance while branch office file servers are complex and difficult to administer and secure.

"FAST™ combines the best of both worlds."

FAST™ allows enterprises to overcome distributed file storage challenges. Thanks to a number of key features, FAST™ combines the best of both worlds, delivering high-performance, secure, simplified solutions for today's distributed enterprise.

Storage Overlay to Windows File Sharing
One of the key reasons why FAST™ is able to deliver such high performance for distributed file storage is its use of storage overlay. In a typical system, users must request each individual file they desire, resulting in hundreds or even thousands of actions. This can cause tremendous latency.

FAST™, on the other hand, can read data in large chunks and save incremental updates over the WAN by providing a local FAST™ Virtual File Share. Essentially, this means that FAST™ compresses and reduces network payload, transforming network storage requests into a more friendly session/application layer protocol, improving streaming between the FAST™ edge and core appliance.

At the same time, FAST™ can terminate user requests, difference file change incrementally and take other actions that further eliminate latency and bandwidth constraints.

FAST™ streamlines data access, improving worker productivity.

Write-back caching
Write-back caching is another invaluable component of FAST™ that addresses the issue of file changes. In a traditional storage protocol scenario, a client will modify a document, then wait for the server to acknowledge the change before sending additional data. This is a time-consuming and frustrating process, especially if WAN delays emerge.

Write-back caching avoids this problem by enabling the underlying Windows Server infrastructure to acknowledge file modification locally and synchronizing the data in the background. Instead of waiting for data to travel to and from a distant server, the user enjoys essentially local behavior, complete with local speeds. The server still receives updates - it's just that the employee doesn't need to wait for these changes to be acknowledged before moving forward. This greatly improves speed and user productivity without sacrificing data accuracy or integrity.

Intelligent File Caching
With FAST™ Intelligent File Caching, employees at remote locations are able to access files and folders from the FAST™ instance, rather than the centralized data center server. This is key, as it offers localized permissions checks and fast file delivery, regardless of whether the network is connected or disconnected. All of this is only possible thanks to the fact that FAST™ fully utilizes the semantics of the Windows Server NTFS file system.

"There is no chance that different users will simultaneously modify a single file."

Coherence and consistency management
Finally, FAST™ delivers coherence and consistency regardless of the number of users, sessions or sites involved by creating leases on files. For the duration of this lease, a master lock exists between the FAST™ core and data center file server, as well as between the client and the FAST™ cache. This means that there is no chance that different users will simultaneously modify a single file or file element, which can lead to confusion and inaccurate outcomes. File integrity is maintained at all times, without the side effect of latency.

The FAST™ difference
With all of these specific features and capabilities, Talon's FAST™ solution is the ideal option for any distributed enterprise that wants to accommodate its remote workers' needs without taking on security risk or administrative complexity. FAST™​'s unique ability to overlay and operate on Windows Server guarantees the best possible performance across the board.

This provides enterprises with a powerful advantage over their rivals, who will continue to struggle with either the latency inherent to data centralization or the security and management headaches that accompany a branch-based approach to file servers. As enterprises continue to become more diversified and widely distributed, i.e. scaling data out from on-premise to hybrid or full cloud storage environments, these issues will only grow in importance, further increasing the value that FAST™ has to offer.

February 18, 2019

Talon and NetApp Enable Enterprises to Utilize a Revolutionary Software Storage Platform

Talon and NetApp work closely to provide businesses with enterprise grade cloud storage and file management. Through NetApp’s Cloud Volumes ONTAP and Talon’...
Continue »

May 31, 2018

Managing Unstructured Data

Data is the cornerstone of an enterprise. It shapes the evolution of corporations and dictates international investments. Unfortunately, many global organizatio...
Continue »

May 29, 2018

The Future of Data Analysis: Fog Computing

To understand fog computing, basic knowledge of edge computing is required. Edge computing, or remote computing, is the current forefront of data analysis and s...
Continue »