Be prepared - wavelength division multiplexing for disaster recovery - Company Operations

Communications News, Oct, 1999

Rely on WDM for disaster recovery.

If any company understands the value of instantaneous, complete data backups, it's EMC Corp. In becoming the world's leader in the growing market for intelligent enterprise storage systems, software, and services, EMC has seen firsthand how companies of every industry are utilizing leading-edge networking technologies to protect their data and investments in time, work, and money.

In 1998, EMC implemented ADVA's optical channel multiplexer (OCM) solution to link its two Hopkinton, Mass., facilities. Without incurring the costs or complexities of running additional optical-fiber strands between the two sites, EMC has realized the security of a comprehensive disaster-recovery strategy. Not only does the wavelength division multiplexing (WDM) system support asynchronous transfer mode (ATM), Gigabit Ethernet, and other high-speed, LAN-application traffic between the two sites, EMC's product-development and other mission-critical data is continuously mirrored. And there is no impact to network performance; all protocols run at their native speeds.

FORESEEING THE UNFORESEEABLE

The primary motivation behind EMC's decision to implement a system for sophisticated data backups was disaster recovery. Paul DiVittorio is Unix support manager for EMC Corp. The underlying responsibility to all of his jobs in that role is making certain that the company's 11,200 employees worldwide have immediate, easy access to customer, product, and corporate data 24 hours a day, seven days a week. If a truck wrecks on the EMC Corp. campus in Massachusetts, taking out a key generator and telephone pole in an instant, DiVittorio is not absolved of that responsibility.

Before solutions such as EMC Symmetrix Enterprise Storage systems and software emerged, enterprise disaster-recovery strategies worked like this: A company backed up its mainframes and other data systems on tape, loaded the tapes onto trucks, and delivered them to a separate, presumably safe remote facility. In the event of a calamity back at the main data center, trucks were sent back out to retrieve the latest batch of tapes. It was a far-from-perfect plan for multiple reasons. The recovered data was only as up-to-date as the most recent truck roll to the remote facility; the process itself was nightmarishly time-consuming. To have hopes of being back up and running on the second business day after a total failure was to be optimistic.

Is it any wonder--what with millions of dollars of revenue per hour at stake in the case of Fortune 500 enterprises--that the clamor for a better way grew deafening?

WDM ARRIVES

Large banking and financial institutions in metropolitan cities were the first, in the early 1990s, to deploy private optical-fiber-based networks between facilities as a high-bandwidth solution for disaster recovery, as well as other business applications (storing data, clustering high-speed computers for parallel processing, handling the facility moves associated with mergers and acquisitions, implementing multimedia business tools, etc.). But networks once thought to provide ultimate scalability are running out of capacity. As Internet Protocol communications grow more prevalent, data traffic is beginning to exceed voice traffic in volume. Video applications have proliferated. Networks are buckling under the weight of heightened, heterogeneous demands on available bandwidth.

WDM emerged to enable improved bandwidth performance over dark fiber. WDM multiplies the capacity of optical-fiber strands, creating "virtual channels." Incoming application traffic is converted to specific wavelengths and multiplexed. Multiple channels are transmitted over the same fibers. There is no performance degradation or specific protocol requirements because light waves of different lengths do not interfere with one another during transmission and are converted back to their original formats at output.

WDM's arrival has been a boon for enterprises. Across distances up to 50 kilometers, enterprises can simultaneously utilize ATM, coupling link, enterprise system connectivity (ESCON), Ethernet, Fast Ethernet, fiber distributed data interface (FDDI), Fibre Channel, FICON, Gigabit Ethernet, SONET, EMC symmetrix remote data facility (EMC SRDF), sysplex timer, and other high-speed, proprietary applications without impact on network performance.

EMC'S NEED

The company's goal was to enhance connectivity between two of its Massachusetts facilities linked by 24 optical-fiber strands. The fiber backbone running between the two sites was exhausted with ATM, Fast Ethernet, and Gigabit Ethernet applications. EMC sought a solution that would make use of the existing infrastructure and prove to be:

* flexible, supporting SRDF and ESCON traffic, in addition to the in-service applications;

* upgradeable, capable of supporting additional, faster protocols as the company's networking needs evolved; and

* protocol-transparent, not requiring the utility to expend resources to physically replace modules or configure data-rate changes.