For 10 years, Energy Trust has worked to increase energy efficiency in the state and saw a prime opportunity in traditional, energy-gulping data centers. The organization recently created a special data center solution that accommodates not only large-scale enterprise and colocated facilities, but also smaller data closets. This offering consists of an IT advisor for every project, a comprehensive menu of equipment and systems eligible for incentives, increased energy modeling incentives to encourage integrated design strategies, and three potential paths to accommodate a range of efficiency goals and innovation levels. Data centers that tap into these resources will maximize energy performance and reduce energy-related operating costs.

The following are two projects that inspired this data center offering. Their stories offer examples of innovation and best practices that will inform anyone looking to build an energy-efficient, environmentally friendly facility.

BendBroadband Vault Data Center, Bend, Oregon

When BendBroadband needed a new data center to power its growing phone, video and Internet services, it set high standards for energy efficiency and green building. Efficient equipment and systems can reduce energy costs, a key selling point for the company and potential tenants, and green building techniques would align with the company’s commitment to sustainability. To achieve its goals, the company enlisted Mildren Design Group and Hewlett-Packard Critical Facility Services to create a cutting-edge design. The team recommended an integrated planning approach, and the company received cash incentives from Energy Trust for holding a comprehensive early design meeting, conducting energy modeling and installing equipment and systems. Energy Trust also provided technical support and engineering expertise.

The team designed the 30,000-square-foot data center to Leadership in Energy and Environmental Design (LEED) Gold standards, with an emphasis on energy-efficiency solutions. To cut costs associated with heating and cooling, the team installed two 450-kilowatt (kW) Kyoto Cooling systems, which take advantage of Bend’s low night-time temperatures to cool the building and equipment. The system includes a UPS flywheel system to help reduce the center’s power usage effectiveness (PUE) ratio to 1.2.

The Vault also features custom cabinets that allow cooling only where necessary. A chimney above each cabinet removes heat produced by the servers. This approach saves energy and supports high-density virtualization, which reduces the fixed energy costs and drives up the efficiency and utilization of the existing servers. Having fewer servers also lowers energy demand and reduces emissions, pollutants and waste. To save even more energy, the team decided to make the cabinets white, instead of a more traditional black design. The white color deflects heat and reduces the amount of artificial light needed throughout the facility by 20 percent.

Energy-efficient lighting fixtures and controls round out the energy-saving equipment. To reduce demand on the power grid, the company also installed a 624-panel 152.9kW solar array on the south-facing roof. This array offsets 16 percent of the energy needs of the fully-loaded data center during peak daylight.

As a result of these strategies, BendBroadband anticipates saving 816,008 kilowatt hours (kWh) of electricity annually. This is equivalent to avoiding the release of more than 355,986 pounds of carbon emissions into the air every year. Energy-saving strategies also helped BendBroadband secure St. Charles Health Systems as the anchor tenant. The Vault’s estimated 30-percent reduction in annual data storage energy costs—savings that equate to a five-year return on investment of $7.1 million for the health-care organization—was a significant factor in sealing the deal.

Fortune Data Center, Hillsboro, Oregon

When Fortune began scouting sites for its new wholesale data center, Hillsboro, Oregon, quickly rose to the top of the list. The Portland suburb offers seismically stable soil, little to no lightning risk, clean power and tax benefits. Like BendBroadband, building an energy-efficient facility was a high priority for Fortune. Reducing energy consumption would contain operating costs, appeal to prospective tenants and demonstrate environmental leadership. Energy-saving techniques would also qualify the company for Energy Trust incentives to offset the cost of energy modeling, equipment installations and building commissioning.

Fortune worked with local firms PKJB Architectural Group and Nova Partners to design the facility to LEED Gold standards. The team consulted with Energy Trust representatives on the proposed energy systems to maximize savings year after year. The completed 240,000-square-foot facility includes numerous energy-saving features for an unprecedented level of efficiency.

To reduce cooling costs, the team divided the facility into hot aisles and cold aisles. By segregating servers that demand cooler temperatures, the cooling system doesn’t have to work so hard to keep the entire center at the proper temperature. The facility also boasts a 99-percent-efficient uninterrupted power supply, so for every dollar of power purchased, 99 percent of it is used instead of dissipating during conversion. Oregon’s mild climate will also allow the center to employ natural cooling methods to run the facility at least 30 percent of the year. As a result, the center’s PUE ratio is just 1.16 in full economization mode, as verified in a Level 5 commissioning process. Fortune expects its Oregon facility to save more than 48 million kWh and reduce carbon emissions by 43 million pounds over the next 10 years. This is equivalent to planting 2.6 million trees.

By prioritizing financial and technical resources for energy efficiency, the industry is able to adopt advanced systems and technologies that may have been cost prohibitive before. This is resulting in rapid progress toward more efficient and sustainable designs that result in reduced energy-related operating expenses and environmental impact. Those are benefits that anyone looking to build a new data center can’t afford to ignore.

The post Securing Data Center Energy Savings in Oregon appeared first on The Data Center Journal.

• Reduce/eliminate disk I/O bottlenecks
• Improve server application performance
• Accelerate access to stored data

Return on Investment (ROI)

• Improved database application read performance by 430%
• Improved database application write performance by 400%
• Improved overall database application performance by 420%
• Improved the average MySQL queries per second by 430%

User Quote

“We put the call out to transition our core databases to solid-state, and only OCZ could give us the reliability and performance our applications demanded.”

Kristopher Kubicki, Chief Architect

Dynamite Data

Introduction

Dynamite Data provides unprecedented retail channel intelligence for merchants, manufacturers and consumers, offering access to the most comprehensive, timely and actionable information. Through its proprietary technology and sophisticated big data collection and manipulation techniques, Dynamite Data automatically extracts real-time data, analyzing and distributing over 30 million extractions per day from nearly a half billion buy pages and more than 3,000 online merchants worldwide. It empowers clients by delivering the most accurate real-time information on channel pricing, product assortment, map violations, ratings and reviews, and stock availability for the ultimate competitive advantage.

Dynamite Data’s comparative shopping service was originally established to compile electronic and high-tech products sold through online merchant buy pages (“e-tail”), but was expanded to include home appliances, sporting goods and children’s toys. Invariably, any product sold online could be developed as an individual Dynamite Data database and be available for comparative shopping or information retrieval. With three billion buy pages available online globally, Dynamite Data’s objective is to data warehouse all e-commerce products for its retail channel.

As part of its original system, Dynamite Data developed a robot (aka “Internet bot”) to automatically read and extract product data from online merchant site maps. The patented Internet bot was capable of extracting approximately 20,000 buy pages per minute or 30 to 50 million buy pages per day, and as of this writing, it has nearly a half billion buy pages stored in its MySQL database. The products in the system center on IT and networking equipment as well as consumer electronic devices, and over time, Dynamite Data was storing approximately three to four terabytes of data each week. These storage demands became very taxing on the initial network and storage infrastructure.

As more products were added to the Dynamite Data retail intelligence data and the web pages were organized into user-preferred formats, data traffic increased significantly, causing I/O bandwidth bottlenecks. The amplified downloading of product comparisons and pricing scenarios resulted in considerable strain on the conventional enterprise hard disk drives (HDDs) they deployed, resulting in suboptimal system performance. It was apparent that an infrastructure upgrade was needed.

Though Dynamite Data deployed additional HDDs to solve disk I/O bottlenecks, the results were still not optimal. The more hard drives that were added, the higher the costs rose for power consumption, cooling and maintenance. And since HDDs inherently have endurance and reliability issues, they required Dynamite Data to implement RAID capabilities so a redundant data path would be in place in the event of hard drive failures. The storage segment of Dynamite Data’s enterprise became expensive and inefficient, and adding HDDs to improve performance was not the solution.

This case study addresses storage challenges that Dynamite Data faced initially in upgrading its retail channel infrastructure to new and improved solid-state capabilities that deliver flash data caching, enterprise-class endurance and reliability, scalability, and real-time access to product data. By adding Deneva 2 solid-state drives (SSDs) developed by storage leader OCZ Technology, Dynamite Data achieved significant improvements in server application performance and data access while reducing overall system costs—solidifying it as a leader in the industry with a trusted and indispensible tool for high-profile merchants and manufacturers.

Dynamite Data’s Network Infrastructure

Dynamite Data created its business model to be the world’s first and premier central repository of all retail channel intelligence, and it uses state-of-the-art big data collection and manipulation techniques to compile comparative information, as well as actionable insights. It does so in Linux-based MySQL; being open source, it enables web page data to be obtained freely. Instead of the merchant providing data feeds for Internet bots to parse, the Dynamite Data Internet bot identifies products and their street prices organically using advanced auto-adjusting natural language processing, giving clients the ability to search for fresh, accurate, comprehensive data, and any product, at any time.

To develop this repository of e-commerce data, Dynamite Data selected MySQL since it is the world’s most used relational database management system (RDBMS) and literally operates as a server to provide multi-user access to a number of the product databases developed by the company. In a comparative retail channel business, user contention must be eliminated and data access must be immediate; this became the mantra for the Dynamite Data upgraded network.

The majority of the web buy pages are created as unstructured MySQL data that must be structured for segmentation within appropriate databases. In turn, this requires write-intensive enterprise performance to store the data. In contrast, as thousands of subscribers access Dynamite Data’s comparative shopping system concurrently, they too will require read-intensive data access performance, eliminating those unpopular delays as subscriber computer screens populate the data. To provide a heightened comparative shopping experience for its subscribers, improvements in read/write performance, as well as an ability to increase the average MySQL queries per server, is required.

The initial Dynamite Data retail channel infrastructure was composed of four AMD 2x six-core 2.2GHz servers that were configured as a read server cluster. The server cluster supported two main applications including MySQL version 5.5 for data warehousing and retrieval, and Sphinx 2.0.4 for full indexing and stored data searches in MySQL. Sphinx works like a database server, and a typical cluster can scale billions of documents and tens of millions of search queries per day powering such top websites as Craigslist and DailyMotion.

From a storage perspective, the original system configuration included four 10,000 rotations per minute (rpm) HDDs per server, all supporting RAID0 striping, resulting in 16 HDDs total for the four-server cluster. The HDDs resided in a dual-socket SuperMicro SAN array connected to the server cluster via SATA. Generating 30 to 50 million buy pages per day challenged the system and created a number of problematic issues. In addition, the initial Dynamite Data network had been operational since 2007, so an IT refresh to improve server application performance and data access was required.

Infrastructure Issues

The excessive downloading of product comparisons and pricing scenarios by subscribers, database loading at 30 to 50 million web pages per day, and network I/O activity (addressing connectivity, communications, management, etc.) caused considerable disk strain in enterprise storage, and using conventional HDDs penalized system performance, resulting in disk I/O bottlenecks. In addition, the MySQL databases did not adequately scale when stored in conventional HDDs, requiring more drives to satisfy the server performance demands. The more drives that were added, the more power and associated cooling was also required, not including maintenance, support and replacement costs, all of which drove up the total cost of ownership (TCO) for Dynamite Data’s initial enterprise.

Although servers can handle millions of input/output operations per second (IOPS), a conventional HDD can only deliver between a 100 and 200 IOPS. As more and more subscribers use the Dynamite Data system concurrently, in addition to the system loading databases with millions of web buy pages daily, the HDDs within the SAN array simply could not keep up with the server workload demands. In addition, HDDs have physical limitations that require their mechanical heads to move for every instance that data is requested from a different location in the storage array, limiting each drive’s physical ability to quickly access random data. Each HDD head movement takes time, and the read/write I/O performance, as well as latency, slows considerably until the data is accessed. As a result, the speed and quality of Dynamite Data’s data collection and manipulation techniques were compromised.

Solid-State Drives

In contrast to HDD storage, solid-state drives store data using NAND flash memory, and with no moving parts, they handle random data access effortlessly. In fact, a single host-based flash SSD can typically deliver random IOPS performance comparable to a large SAN array with hundreds, if not thousands, of HDDs incorporated. Dynamite Data realized that adding SSDs to its enterprise would significantly improve its MySQL and Sphinx database performance. But the real benefit would derive when “hot” data could be cached on SSDs residing in the host physical server, providing significantly faster data access to database indices.

In preparation for adding SSDs to its network infrastructure, Dynamite Data required SATA-based SSDs with leading-edge performance, enterprise-class reliability and endurance, and support for open-source Linux-based MySQL and Sphinx databases. It was Dynamite Data’s intent from an IT perspective to have the entire networked system and applications on SSDs, without having to rely on hard disks.

After researching competitive enterprise SSDs, Dynamite Data selected SATA 6Gbps-based Deneva 2 SSDs from OCZ Technology, one of the leading providers of solid-state storage solutions in the world. Since databases need to be transactional so that data becomes instantly available, the Deneva 2 SSDs are ideally suited to the Dynamite Data databases, delivering 80,000 IOPS (random 4K writes) with a maximum throughput of 525MB/s and supporting 480GB capacities and 2.5-inch form factors. They also provide power loss data protection, best-in-class endurance (e.g., minimal write amplification, intelligent block management and wear-leveling), and advanced encryption and error correction coding (ECC), making these drives ideal for enterprise applications.

“We put the call out to move our core databases to solid-state, and only OCZ could give us the reliability, scalability and performance that our applications demanded,” said Kristopher Kubicki, Chief Architect for Dynamite Data. “With these improved enterprise capabilities, the implemented Deneva 2 SSDs will enable us to collect and manipulate even more data while providing our clients with heightened experiences.”

Testing and Implementation

Before implementation, Dynamite Data conducted extensive performance tests to gauge the improvements that OCZ flash-based SSDs provide, especially with the ability to cache data on flash for significantly faster data access to stored database indices. The test environment was a scaled-down version of the actual Dynamite Data infrastructure and included the following:

• 4 Read Servers: AMD 2.2GHZ, 2 x 6 core CPUs
• Key Applications: MySQL v5.5 and Sphinx 2.0.4
• 2 HDDs 10k RPM with RAID0 redundancy
• 1 SSD OCZ Deneva 2 with 480GB capacity

One set of tests conducted by Dynamite Data tested the read and write IOPS performance of the OCZ Deneva 2 SSD versus a small hard drive array. The tests, which were run for at least one week to determine a performance average, included constant downloading of product comparisons and pricing scenarios, database index loading of millions of web pages per day, and general network I/O activity. The results are as follows:

With MySQL being the dominant database in its infrastructure, Dynamite Data tested the average MySQL queries per server over a one week period between the OCZ Deneva 2 SSD and the small hard drive array. A typical MySQL query could range anywhere from downloading product comparisons to generating pricing scenarios, or identifying discount, rebate or shipping cost scenarios, and so on. The average MySQL query results (per server) are as follows:

Conclusions

As outlined in this case study, the intense downloading of product comparisons and pricing scenarios by clients and the loading of millions of web pages per day, in combination with general network I/O activity, caused considerable disk strain in Dynamite Data’s enterprise, and using conventional HDDs caused disk I/O bottlenecks and penalized system performance. The MySQL database indices did not scale very well in conventional HDDs requiring more drives, more RAID, more power and cooling, and more maintenance, all of which drove up TCO for Dynamite Data’s enterprise.

The storage challenges that Dynamite Data faced required solid-state capabilities to enable flash data caching, enterprise-class endurance and reliability, scalability, and real-time access to information. In an online comparative retail channel business, user contention needs to be eliminated and data access must be immediate. By adding OCZ Deneva 2 SSDs to its infrastructure, Dynamite Data achieved significant improvements in server application performance and data access while reducing overall system costs. But the real benefit enabled data to be cached on SSD flash, providing significantly faster access to database indices, and implementing SSDs into the infrastructure would hopefully improve system performance four to five times over the previous HDD configuration.

To provide a heightened comparative retail channel experience for its clients, improvements in read/write performance, as well as an ability to increase the average MySQL queries per server, was required. After extensive testing, Dynamite Data achieved its system performance goals versus its hard drive model:

• Read IOPS performance improved 430%
• Write IOPS performance improved 400%
• Total IOPS performance improved 420%
• Average MySQL queries improved 430%

“The OCZ Deneva devices were unique in that they were the first available eMLC solutions with rock star controllers, and featuring enterprise-class write durability, eliminated the drive endurance issues and associated costs that were typical with our initial disk storage infrastructure,” said Brian Stratman, Systems and Database Engineer for Dynamite Data.

With three billion buy pages available online globally, Dynamite Data’s objective to data warehouse all retail channel products and provide immediate access to product comparisons and pricing scenarios is now a reality with the addition of OCZ Deneva 2 SSDs to the infrastructure. The ability to cache data on flash provides much faster access to information and an improvement in server application performance, ultimately enabling Dynamite Data to provide its clients with unmatched critical, competitive and actionable insights on retail channel big data, while delivering the optimal user experience.

The post Dynamite Data Improves MySQL Performance and Access to Comparative Online Product Information with OCZ Deneva 2 SATA-Based SSDs appeared first on The Data Center Journal.

That approach works great when building a brand new facility and when you don’t need to have the data center close to a population center. But what happens when you must be located in urban areas where space is at a premium and summer temperatures soar?

“There is a cumulative effect because all day long the heat cooks the bricks and they cumulatively heat up deeper and deeper and don’t return to ambient temperatures at night,” says the assistant chief engineer for the data center of a multi-billion-dollar financial institution in New York City.

With outside temperatures over 100 degrees and significantly hotter on the roof where the condensers were located, the data center was at risk of having to shut down when temperatures exceeded safe operating levels. By installing a MeeFog system to cool down the air entering the rooftop condensers, the financial company increased the amount of equipment in the data center without tripping offline during summer heat waves.

Keeping up With High-Frequency Trading

In most cases, latencies of a few milliseconds are fine. Users never notice the difference. But for high-performance processing, shaving micro- or nanoseconds is what it is all about. The larger the on-die cache, the better the CPU performs. A specially designed computing appliance, therefore, can outperform an assemblage of discrete components.

Fiber optic networks are fast, operating at roughly two-thirds the 186,000 miles per second that light moves in a vacuum. Using a fiber optic cable running from Yahoo’s Lockport data center to Wall Street would get the data there in about three milliseconds. But with the growth of high-frequency trading (HFT), that latency is far too slow. Financial institutions don’t have the option of using a remote data center; the computers must be located as close to the market as physically possible to eliminate the milliseconds or microseconds it takes to transmit data.

HFT involves analyzing massive amounts of data to locate small opportunities for profit. For example, there may be a slight difference between the exchange value of the Swiss Franc between the London and Frankfurt markets, or between the bid and ask prices on a share of stock. Those opportunities may only exist for less than a second. During that time the HFT company must locate the opportunity and execute both the buy and sell transactions. Although the profit margin on each trade is small, by executing thousands or even millions of such transactions daily, companies make billions of dollars in annual profit. HFT now accounts for more than 70% of trades on U.S. equity markets, and a growing percentage of trades in other countries.

To accommodate HFT, the markets have sped up their own systems and now offer an average three-millisecond latency on transactions—far less for some. For example, Millennium IT, which is owned by the London Stock Exchange, offers a platform that can execute more than 500,000 transactions per second with less than 100 milliseconds latency total.

To operate successfully, therefore, a trading firm can’t afford to work from a remote data center, or even to use fiber optics. Instead, it uses microwave transmissions to connect the data center to the trading floor. This means that it is stuck with whatever environmental conditions exist in that city.

Heat Wave Hassles

The financial institution in question operates two mirrored data centers to service its New York City operations. One of these facilities occupies the second floor in a 14-story brick building, which was originally built in 1912 to house a department store but now is a multitenant structure hosting computing and telecom equipment. The 87,000-square-foot data center contains about 30,000 square feet of white space for the computing and storage equipment and a small amount of office space. The rest of the space is for battery rooms and other ancillary equipment.

Unlike rural data centers, which can pull in enough outside air to keep the data center cool, this data center is in the middle of a dense urban area where the streets and brick buildings absorb the heat day after day and don’t fully cool down at night, gradually raising the temperature inside the building.  To make things worse, although the urban ambient temperatures themselves are higher than the surrounding countryside, the rooftop temperatures can exceed the ambient temperatures by another 10 degrees.

This NYC data center uses an indirect cooling system with computer room air conditioning (CRAC) units in the white space. Glycol runs through heat exchangers in the CRAC units and is then pumped to rooftop units where it is recondensed and the heat dissipated into the outside air.

When the data center went through a major upgrade that added to the heat load, there was enough room on the roof to install five additional condensers to supplement the eight already in place. This arrangement works for most of the year, but for a few weeks each summer it is insufficient. The cooling system operates properly as long as the glycol temperature can stay below 100 degrees. When it exceeds that temperature, the cooling system can trip off line.

“We have dry coolers on the roof, so we don’t have the benefits of evaporation,” says the data center’s assistant chief engineer. “If we have 1,000 tons of refrigeration at 100 degrees, when it goes to 110 degrees capacity drops and we are just shy of what we need. On very hot days when it gets above 110 degrees on the roof—which we reached about 10 days last year—the units would have tripped offline on high head pressure.”

Cooling Down the Inlet

To keep the data center operating, since there was no room for additional rooftop condensers, the financial institution needed to find a way to get more cooling out of the condensers it did have by bringing down the inlet air temperature. After experimenting with using lawn water sprinklers to spray water into the inlet air on the bottom of the condensers, it decided to put in a more efficient and controllable MeeFog system to keep the glycol temperature and pressure within limits.

Mee Industries has been building fogging systems since former Cornell University researcher Thomas Mee, Jr., founded the company in 1969. These systems use high-pressure pumps and specialized impaction pin nozzles to break the water down into a fog of droplets. At 2,000psi, these droplets average less than 10 microns in diameter, or about one-tenth the width of a human hair. The droplets rapidly evaporate, lowering the temperature of the air.

Nozzles produce billions of tiny fog droplets that evaporatively cool the inlet air close to the wet bulb temperature.

The company designed a system for this application that consisted of a single 10HP, 480V Grundfos CRI-5 pump with Allen Bradley controllers to pressurize the water for all use by the eight original condensers. Three-quarter-inch stainless steel feed lines bring the water from the pump to the 90-nozzle fogging arrays placed in the bottom inlet of each of the condensers. A Marlo, Inc., water-softening system keeps minerals from clogging the nozzles or building up on the condenser fins.

“The MeeFog system pressurizes the water to just under 1,000psi, and when it comes out of an orifice in such a fine fog, it cools the outside air and drops the temperature of our glycol by about six to eight degrees,” says the engineer.

Putting It to the Test in the Data Center

Once it was installed, the fogging system was quickly put to the test in a heat wave last summer. By the third day of the heat wave, the rooftop temperature hit 115 degrees, even though the air temperature was just 103 degrees.

“Since we were above our 100 degree max, our cooling capacity was below what we needed,” says the engineer. “We didn’t wait until we had units failing, but fired up the MeeFog unit as soon as the temperature hit 100, and the glycol temperature dropped about six degrees. As the day progressed and the outside temperatures climbed, our glycol temperature didn’t get any higher, so the fog cooling effect was pretty substantial.”

Nozzles produce billions of tiny fog droplets that evaporatively cool the inlet air close to the wet bulb temperature.

Nozzles produce billions of tiny fog droplets that evaporatively cool the inlet air close to the wet bulb temperature.

Currently the system is only cooling the bottom inlet air, which is enough to meet the original intention of keeping the data center online during heat waves, but an engineering firm has been to the site and is looking at fogging the condensers on three sides to provide additional cooling and reduce the amount of energy required to cool the data center. If successfully implemented, this system addition could considerably reduce overall cooling costs.

Nozzles produce billions of tiny fog droplets that evaporatively cool the inlet air close to the wet bulb temperature.

The post Keeping a Data Center Cool in the Summertime City appeared first on The Data Center Journal.

ipHouse’s hosting product line includes cloud hosting of virtualized servers and data centers, dedicated physical server platforms and highly scalable, clustered web and email hosting for corporations, government entities and nonprofits.

ipHouse’s virtualized servers and data centers run on a VMware vCloud environment built on Dell servers, with CrashPlan PROe backups, and LogicMonitor monitoring. The environment was built with fault-tolerant NAS storage from the beginning to deliver a high level of reliability and performance. Although chosen with the expectation that it would scale as the product grew in popularity, the initial storage system for the platform could not keep up with the product growth. After a struggle to optimize the original storage system to enable it to keep pace with server growth, the company switched to a Tegile Systems Zebi storage array. The change has transformed the storage responsiveness and, with it, customer satisfaction.

Challenges

The success of the virtual server and virtual data center product line created storage latency issues that significantly affected ipHouse’s ability to continue expanding the business. “Our customers range from single proprietorships to large corporations running all aspects of their business on servers within their own private virtual data center. Different kinds of customers put different demands on the platform and the storage systems. One customer may just have a single, low-demand server, but the next may have a real-time interactive client program on their servers. These customers need a high level of performance in order to satisfy their clients,” said Mike Horwath, CTO at ipHouse. “We carve out a section of our VMware clusters for our customers to run their networks in. Since we don’t know exactly what our customers are going to do or when, consistently high I/O is a key requirement. It’s not necessarily about throughput, it’s about input and output to the storage systems.”

Poor I/O performance had serious consequences for both customers and ipHouse’s business. “Latency, or how long it takes an I/O to occur and return, was starting to creep up on our old storage systems, and that was starting to cause problems,” said Horwath. In addition, some prospective customers turned away from ipHouse because Horwath was honest about the storage issues. “We moved data around as best we could and tried to stabilize the systems, but the problem persisted,” he said. “Eventually, it became obvious we needed new storage.”

Horwath went to the VMworld conference in August 2011 and started talking to storage vendors about his concerns. “I was looking at newer storage vendors rather than the big guys like EMC or Hitachi,” he said, “because I knew their pricing and it was beyond what we could afford.”

Tegile Systems wasn’t at VMworld, but Horwath heard about the company there. He began discussions with Tegile Systems, and he took delivery of an evaluation unit in December 2011 along with evaluation units from two competing companies.

“Tegile did very, very well in my benchmarking,” said Horwath, “and they worked with me on anything that occurred. If I had any questions, they would bring up a WebEx session and we would work on them together. Most of the issues I brought up they had answers for, and when they didn’t have the answer they would go and find the answer so I was never left hanging with an open issue.”

The Zebi Storage Solution

Thanks to his successful trial, Horwath bought a Tegile Zebi HA 2100 EP system featuring 40 terabytes of storage and 8,200-gigabyte SSDs. Unlike competitive storage systems, Zebi features a two-tier caching infrastructure that accelerates disk I/O performance. Tier 0 is volatile DRAM memory and Tier 1 is non-volatile solid-state disk (SSD) drives. In addition, Zebi incorporates Tegile’s Metadata Accelerated Storage System (MASS), which stores all metadata (data about the data) on the high-speed SSDs to further improve read/write performance by accelerating random and sequential I/O, data deduplication, compression, snapshots and RAID rebuilds.

“Tegile’s MASS architecture really brought us up to peak performance,” said Horwath. “After the evaluation process and bringing the new box into production, customers were amazed at the improvement in service responsiveness. Every customer came back with positive feedback—any issues they had been seeing were now gone.”

The Tegile array has transformed ipHouse’s business, increasing IOPS performance by 400 percent with no appreciable latency. In addition, Zebi’s built-in deduplication and compression are also delivering more space than ipHouse purchased. “Between de-dupe and compression we are running at about 40-45 percent savings,” said Horwath.

Results

The Zebi storage array has eliminated Horwath’s major headache in running his data center, and it has enabled the company to deliver the highest performance for its customers.

“Zebi removes a big chunk of stress off my shoulders,” said Horwath. “It has caused the whole I/O latency issue to go away, and customers are thanking us for taking care of the problem. We have a couple of potential customers who were waiting for us to fix the problems. We’re talking again and should soon bring them onboard.”

Horwath says that he expects new business growth to increase his investment with Tegile. “Now that the big albatross that was holding us back is gone, we are able to continue the rapid growth of our server hosting products,” he said. “I look forward to seeing what goes on over the next few months. I’m hoping I can call Tegile back in six months and say I need another unit. What I buy from Tegile depends on whether we need more storage space or whether we’re running out of CPU performance on the controllers. One of things I liked about Zebi is that I can add another drive shelf to the existing unit to get more storage capacity. If I need more CPU performance I’ll buy another unit.”

In addition to a great product, Horwath feels that Tegile is a great company to work with. “Tegile has been incredibly easy to deal with,” he said. “They have been personable and human to talk to—I don’t feel like just another customer. When I send them messages they respond back. I tell them what I’d like to see in the next version of the software, and they seem to care about those reports. So far, the experience has been positive with every person I’ve talked to.”

All in all, the Zebi system has brought much higher performance to ipHouse’s hosting services, enabling the provider to deliver optimum solutions for its current customers and to improve its future business prospects in the bargain.

The post Case Study: Midwest Server Hosting Company Transforms Its Service Responsiveness and Customer Relations With Tegile Zebi Storage Array appeared first on The Data Center Journal.

One of the world’s largest manufacturers of contact lenses faces the challenge of managing a highly distributed and complex global network infrastructure while ensuring compliance with strict security and compliance standards and reducing downtime.

With IT systems becoming more strategic to CooperVision’s operations, a critical step was needed to enhance and modernize its out-of-band management network solution in order to strengthen business continuity and reduce the number of security threats. Given the ever increasing number of new, potential security threats, the out-of-band Management Gateway needed to keep pace with their current corporate security policies and mitigate exposure to future threats. CooperVision also wanted to provide secure remote access, which would boost productivity and flexibility.

With locations distributed around the globe in 12 countries, CooperVision was compelled to find a solution that could:

• Ensure security compliance with certificate-based VPN connections.
• Manage its network infrastructure remotely and securely  out-of-band in order to minimize downtime and reduce on-site technician visits.
• Achieve disaster recovery compliance at remote locations that lack immediately available IT personnel.

As a result, CooperVision uses Opengear IM4200 advanced console servers to enable its central support team to perform reliable and secure data center management of its IT assets distributed across the world. Likewise, they wanted to ensure high availability for the support team that uses secure out-of-band access via 3G GSM cellular connectivity.

Encrypted VPN Connectivity to Remote Sites

The Opengear IM4200 delivers  enterprise-grade security for remote monitoring, access and control. Opengear’s next-generation management appliances support the industry’s most stringent security, encryption and AAA (authentication, authorization, and accounting) requirements, ensuring that management policies are always enforced, even during a network outage. Opengear solutions maintain and enforce AAA policies that protect distributed network and IT infrastructure from security threats with:

• OpenVPN and IPSec enterprise-grade PKI VPN remote access over primary or out-of-band connection
• FIPS 140-2–compliant OpenSSL cryptographic module, certified for use in the U.S. Government
• Two-factor authentication using RSA SecurID
• Enterprise0grade firewall

Cellular Out-of-Band Connectivity

The IM4200 cellular-enabled solutions reduce the complexity found in traditional dial-in out-of-band applications where international dialing costs and restrictions prevent ease of access. Equipped with built-in failover capability, the IM4200 appliances automatically switch from primary wired connections to wireless mobile broadband network during primary service outages and will automatically fail back without interrupting service.

This access is available even when the remote console server has private non-routable IP addresses, which is often the case when the console server is connected via a cellular modem connection. Opengear’s cellular enabled IM4200 can answer out-of-band connections that are initiated remotely, or they can be configured to initiate the outbound connection from the remote site using Call Home features.

Granular Logging With Localized Storage

Opengear appliances provide a selection of monitoring facilities that help diagnose the cause of problems and support Sarbanes-Oxley, GLBA, NERP and HIPAA conformance.  The console server can maintain a record of all the direct access and communications with the serially managed devices and network-attached devices.  A log of all system activity (syslog) is also maintained and stored locally on 16GB of internal flash memory.

To ensure compliance with internal audits, CooperVision relies on the IM4200’s robust logging and reporting capabilities even during outages. Additionally, the IM4200 provides real-time log inspection capabilities. This enables the IM4200 to generate alarms or trigger automated actions when specific patterns are identified in the log data.

Business Continuity on a Global Scale

Global companies require secure and dependable access to their large network of devices spread throughout the world.  Maintaining continuity of the business operations and processes is vital to success in a competitive market. CooperVision selected the Opengear IM4200 as a key component in a major disaster recovery initiative targeted at enhancing reliability and uptime of its distributed network infrastructure located in 12 countries across five continents.  The IM4200 gives CooperVision the most advanced GSM cellular features on the market today for proactive out-of-band management of their business-critical network infrastructure.

The post CooperVision Finds Strategic Advantage in Global Deployment of Opengear Gateways for Out-of-Band Access appeared first on The Data Center Journal.

Atotech was founded in 1993, when the Elf Atochem Group merged its M&T Harshaw operations with Schering Electroplating Division, having a deep history in electroplating dating back to 1901. Today, Atotech is a direct subsidiary of the world’s fifth-largest oil and gas company Total, created from the merger of TotalFina and Elf Aquitaine in 2000. Atotech is one of the world’s leading suppliers of integrated production systems, chemistry, equipment, know-how and service for decorative and functional electroplating, semiconductor and printed circuit board manufacturing.

Next to the core business units: GMF (General Metal Finishing) and Electronics (Printed Circuit Board Production), additional business units such as Electronics Materials and Wafer play an increasingly important role for the future growth of Atotech and its customers. Headquartered in Berlin, with locations in all important industrial regions of the world, Asia, the Americas and Europe, Atotech is a truly international company employing over 3,600 people in more than 40 countries.

Business Challenges

To support their exponential growth, Atotech wanted to ensure transparency in its access management system. Management needed to save time, reduce costs and ensure trust in their data and people, while being able to easily control internal access management processes. Access authorizations had previously been performed manually by local or central administrators. Atotech researched the market to identify software that could intuitively support and manage their access authorization requirements. 8MAN Access Rights Management from Protected Networks provided the ease of use, transparency, flexibility and reporting that Atotech had been looking for.

Critical Requirement—control file server and Active Directory permissions:

• Regulate who can access business-critical data
• Tangibly reduce amount of time spent by administrators on authorization management
• Streamline access rights to sensitive data and thereby curtail the impending risks

Protected Networks’ Solution: 8MAN

8MAN, which is essentially information trust software, analyzes and evaluates existing access authorizations, providing IT and data owners with a graphical overview of user and group access authorizations and thus enabling informed control and management. The solution graphically represents the assigned rights, automates processes and optimizes standard operating procedures.

Key Business Benefits

• Automated Processes: The IT department is often caught up in daily, repetitious tasks, particularly around managing access rights. With 8MAN, the group wizard automates these tasks, reducing the scope for human error and increasing productivity by accelerating the process by up to 90 percent. Once the requirements have been specified by the administrator, 8MAN provides a fully automated authorization assignment process, thereby minimizing potential errors. In addition, valuable data can be archived in an audit-proof format, thus satisfying business legal requirements and allowing audits to be completed quickly and effortlessly.

“The administrators can view their active directory from a completely new perspective: for example, the users, groups and their relationship to one another are illustrated as dynamic graphics in a tree structure or a list. You have the option to access actively—just by drag and drop,” commented Stephan Brack, Managing Director, Protected Networks.

Compliance and Control: Business-critical data is an irreplaceable asset. When basic questions such as who can view and access data cannot be confidently answered, there is a real threat to the overall integrity and confidentiality of the organization’s data assets.

“8MAN has highlighted how access rights given to trainees who pass through various departments, ex-employees and project staff are often not revoked when they leave the company or department,” said Stefan Brüggemann. 8MAN immediately identifies the flaws in the permissions caused by improper or outdated approvals and provides a trustworthy solution to review and manage access permission. Employees, trainees or project staff who are required to have access rights during the period of their employment can all be set up quickly and easily, but more importantly upon termination, departmental transfer or project completion, 8MAN automatically cancels the rights.

8MAN has been installed in four different locations including Austria and the Czech Republic, and is already helping Atotech to save time and money, but perhaps more importantly it is allowing the organization to have trust in its data and people.

About Protected Networks: Founded in 2009, Protected Networks GmbH is a Berlin-based company that develops integrated solutions for access rights management of server environments across all business sectors and at public authorities. The solution, 8MAN, is information trust software based on an innovative approach to integrated data security management and offers uniform and automated management of user rights. Clients thereby save cost and time while increasing protection against unauthorized internal access.

The post Case Study: Protected Networks' 8MAN Helps Atotech appeared first on The Data Center Journal.

Based in Denver, Colorado, Cimarex Energy, Co., is an independent oil and gas exploration and production company with primary operations in the Mid-Continent, Permian Basin and Gulf Coast oil areas of the U.S.  With an extensive roster of geoscientists and exploration teams, Cimarex is focused on assessing and generating drilling prospects and programs—determining which reserves will deliver optimized production rates and a strong return on investment. In 2010, the company’s proved reserves totaled 1.88 trillion cubic feet.

Cimarex employees are in constant contact with external stakeholders such as land and well owners, regularly sharing large documents that contain sensitive data: financial, tax and other personal information. In addition, the company works closely with graduate students at local universities who conduct ongoing research for exploration projects, collaborating on sensitive findings related to simulation flows, seismic data and mapping documentation. The company actively recruits from these universities, so ensuring a professional, positive experience for students is key.

Challenges

To handle daily communication exchanges with the company’s key external audiences, Cimarex originally deployed two different vendor offerings: Accellion Secure File Transfer and Microsoft SharePoint. Accellion was originally implemented as a more secure and user-friendly alternative to FTP services, giving employees the freedom to share documents larger than 20MB, while offloading large files from the company’s email system.

SharePoint was used for collaboration and document sharing with students, but it was not a viable, long-term solution for the company. The product’s licensing structure did not support Cimarex’s business operations, as the company could not predict the number of student users year to year, resulting in significant product price jumps in order to scale as needed.

Ultimately, Cimarex wanted to make it as easy as possible for employees to collaborate internally and externally, while ensuring that the medium of choice could support unlimited end users and was cost effective, and while also making IT’s life easier with minimal administration.

“We needed simplicity without compromising function,” said Rey Mirabal, Network Systems Engineer with Cimarex. “Our users were already familiar with Accellion as a file transfer solution, so it was a natural progression to move to Accellion Secure Collaboration for all of our file-sharing needs.”

Secure Solution

Cimarex conducted a two-month trial of Accellion Secure Collaboration, initially using the solution for its work with the University of Oklahoma. With Accellion, Cimarex employees created secure workspaces for research to be reviewed, shared and revised—giving graduate students and staff a central place to collaborate on current exploration projects. Owing to the positive feedback from Cimarex employees, the company decided to deploy Accellion Secure Collaboration for use across all four office locations.

Today, each university program has its own workspace, with an individual Cimarex employee acting as the administrator—relying on the product’s intuitive end user application to determine who has posting privileges, viewing rights and so on. Ensuring that workspaces were not visible to everyone was an important security feature for the universities, as much of the research contains proprietary information.

“Accellion provides our partners with the peace of mind that their confidential files remain confidential,” said Mirabal. “We can now send, receive, and share information in a highly secure and safe environment, and it’s a part of how we do business every day.”

Cimarex deployed Accellion in its existing VMware virtual environment, providing the flexibility to scale as the company’s needs evolve, enabling collaboration with any number of users. The product’s scalability has translated to significant cost savings, reducing the company’s annual IT expenses by more than 20 percent following its transition from SharePoint.

“As an IT person, if I can save time—and money—it’s the ideal combination,” said Mirabal. “Accellion has improved how we communicate and reduced our costs, proving its worth and then some.”

The company continues to rely on Accellion’s secure managed file transfer capabilities, with its legal department and other staff members sharing sensitive, data-intensive 100GB+ files. With Accellion’s LDAP integration, Cimarex employees are automatically validated with existing network accounts and passwords, adding to the solution’s user-friendly experience.

Benefits

• Reduced storage needs and costs
• Ease of IT Administration
• Secure global collaboration
• Full reporting and tracking

Specifications

The post Secure File Sharing in Architecture, Engineering and Construction: Cimarex appeared first on The Data Center Journal.

Situated in Beaverton, Oregon, EasyStreet recently built a new SAS 70 (the Statement on Auditing Standards No. 70) Type II audited data center and also finished an energy-saving retrofit to its first data center. EasyStreet buys 100 percent renewable power offsets for both data centers as part of the Portland General Electric Clean Wind Program. “Three years ago we started buying wind offset credits for our first data center. We initially bought offsets for fifty percent of our power consumption. We gave our colocation customers the opportunity to participate in that program, paying a small up-charge to be able to put a Portland General Electric Clean Wind logo on their website, which means that we’re all participating in the program together,” said Jon Crowhurst, director of technical services for EasyStreet. The company has now received confirmation from the utility that both data centers are zero-carbon-footprint energy consumers. According to Crowhurst, “That’s part of our plan moving forward.”

Pioneering Data Center Design

Owing to the energy efficiencies gained compared with conventional data center designs, this is the first data center project to qualify for funding through the Oregon Department of Energy’s Small Scale Energy Loan Program (SELP). With the help of the Energy Trust of Oregon, EasyStreet played a pioneering role in developing the Oregon Department of Energy’s expertise in the area of efficient data center design. Through careful planning and implementation of energy-smart technologies and systems, EasyStreet estimates that it will be able to save 1,532,634 kilowatts a year—enough energy to power 153 average households.

EasyStreet, which has won many accolades for its business and green initiatives (including being an EPA Green Power Partner), offers a wide selection of data center–based and Internet-access solutions. Some customers want the flexibility and control that comes with EasyStreet’s colocation services. Others prefer managed-server offerings with EasyStreet being responsible for administration and monitoring of system hardware and software, backed by service-level agreement (SLAs). Regardless of the type of service EasyStreet provides, system uptime and availability are prime concerns. “Making sure that the customer’s computing systems have available power is paramount to not only keeping systems up and running at high nines (9s) of availability, but for us to keep operating as a viable company. Power outages, if not remedied, can cost organizations thousands, if not hundreds of thousands, of dollars every minute computing systems are down. If EasyStreet can’t maintain power integrity, customers will go elsewhere,” said Crowhurst.

Greening the Power Infrastructure

The majority of data center power consumption that can be made green is the cooling system; but Crowhurst and his team extended their green design throughout the data center, including the purchase of energy-efficient uninterruptible power systems (UPSs) and energy-efficient transformers. When it came to considering the UPS system, it was obvious that a battery-based UPS would fail to meet EasyStreet’s sustainability initiatives. “Batteries are not environmentally friendly, as you can imagine,” said Crowhurst. Valve regulated lead-acid (VRLA) batteries are inherently problematic to the environment, as they contain toxic chemicals and must be frequently replaced. Another important point is that batteries require expensive cooling to operate per specification. If not properly cooled, for example, batteries will degrade, quickly putting the power-protection infrastructure at risk.

Data center UPS battery bank

Reliability is the major concern. “We have two battery-based UPSs that we’ve had for almost 12 years. While the UPSs themselves have been reliable, we’ve experienced three failures of the batteries. We do preventive maintenance every quarter as the factory recommends, and still we weren’t able to avoid battery failures,” said Crowhurst. One bad cell in one battery of a chain of “maintenance-free” lead-acid batteries is enough to bring down the whole set. They also require an excessive amount of testing, monitoring and maintenance to ensure against such occurrences.

For EasyStreet, building a new data center meant looking at all the green technologies available; reliability was always the number-one consideration. So when it came to energy storage, Crowhurst looked to VYCON to learn more about its clean energy storage systems—flywheels. An important consideration of implementing flywheels is that they had to be able to work with double-conversion UPSs. VYCON’s VDC-XE units were the perfect fit, as they easily pair with highly efficient, double-conversion UPS systems. “I visited the VYCON factory and looked at how the flywheels were made. VYCON’s experience and history in the marine and rail industry is a fairly impressive use of the technology—shows how rugged they are,” reflected Crowhurst.

Environmentally Friendly Energy Storage

VYCON’s VDC flywheel systems store and deliver a reliable source of DC power using the kinetic energy of a high-speed flywheel. Compatible with major brands of three-phase UPSs, the systems interface with the DC bus of the UPS, just like a bank of batteries, receiving charging current from the UPS and providing DC current to the UPS inverter during discharge.

The patented technology enables the VYCON flywheel to charge and discharge at high rates for countless cycles without degradation throughout its 20-year life—unlike traditional batteries.

Another key advantage for EasyStreet is the significant space savings of the flywheel systems over batteries. A battery plant is approximately three times the size of a comparable-size flywheel. “As a colo, space is a precious commodity. The more space we have, the more we can accommodate our customers’ servers and other computing assets,” affirmed Crowhurst.

Flywheel systems were not new to EasyStreet, as they had experience with one from another manufacturer for their previous data center. But maintaining and replacing bearings with a cost of nearly $10,000 every few years was an issue. “Having to replace the bearings in the other flywheel system is a relatively expensive maintenance operation, and the unit is out of service for six to eight hours,” stated Crowhurst. The VYCON VDC-XE does not require any bearing maintenance.

Debunking the Myth of Battery Backup

In the new data center, EasyStreet has three VYCON VDC-XEs running in parallel with double-conversion UPS systems. If there’s a power outage, the 300 kilowatt flywheel systems act as a bridge that seamlessly transfers to the facility’s diesel-engine generators. Crowhurst explains why backup batteries are not needed. “Having 30 minutes or half an hour of batteries is, in my opinion, pointless. If the generator doesn’t start in the first 30 seconds, there’s nothing you can do. If you had two generator mechanics with their tools in hand, standing next to the generator, and said, “I need this fixed in 14 minutes,” they’d both laugh at you, because there’s nothing that can be done to diagnose or repair a problem with the generator in the time allowed. A well-maintained generator plant doesn’t need 15 minutes of batteries.”

The Future

As EasyStreet’s new data center becomes more populated and energy demands increase, Crowhurst will add more UPSs and VYCON flywheels. “The end stage is three UPSs with 18 flywheels total,” envisions Crowhurst. “Reliability, sustainability and having a low carbon footprint are part of the ethos of our company. This vision with actual energy savings allows us to save money, which translates to saving our customers money—it’s a great win-win.”

The post EasyStreet Keeps Its Green Data Center Trouble-Free With VYCON Clean Energy Storage Systems appeared first on The Data Center Journal.

The Challenge: Enable Quick Recovery of Business Operations During Downtime Events

Niemann Capital Management is headquartered in Scotts Valley, California, and uses a Silicon Valley–area Equinix facility as its primary data center. A secondary site is located in Carson City, Nevada, for recovery. The company’s IT infrastructure is largely Windows based and virtualized, with at least 150 virtual servers. NCM was doing backups directly from production machines to disk, and it also supplemented these with tape backups that were stored offsite to meet the retention requirements of current compliance legislation. Numerous feeds come in daily from financial institutions to NCM’s mission-critical SQL servers, providing the information necessary for advisers to make investment management decisions. It was important for the company to be able to recover quickly from a downtime event, as well as have a backup process in place that did not affect the production environment.

“When you’re managing other people’s money, you’re highly accountable for everything that goes on, and the liability can be pretty extreme,” said John Etheridge, IT Director, Niemann Capital Management. “In our business, if the servers go offline or we have downtime at the wrong time in the day, that hinders our ability to trade, distribute funds, liquidate and so forth, so it’s critical for us to be able to recover our data and maintain operations. In the past, if I were to lose a site, the best I could hope for was to get back online in two days. It would then take another 12 days to get everything running at full capacity, and that just wasn’t acceptable. My goal was to find a solution with the recovery capabilities we needed, within the parameters we had to work with.”

The Solution: Application-Consistent Recovery With InMage

As he began the search for the right recovery solution, Etheridge analyzed such factors as the number of IT personnel, financial commitment and time commitment that each product would ultimately require.

He initially considered the strategy of fault-tolerant sites, but in the end decided the return-on-investment was not compelling enough.

“I call it the 100-mile limit,” said Etheridge. “Even if we have a fault-tolerant scenario with two sites running real-time data, any time you get past that 100-mile limit, you have a significant problem to deal with because of the distance the data has to travel. Fault-tolerant sites are very expensive and require a lot of maintenance, work and personnel. The ROI just wasn’t there, so we decided to look for other solutions that focused on bringing our primary site back online.”

“There wasn’t a single solution out there that we didn’t evaluate,” continued Etheridge. “We looked at the very mature products, yet they still had limitations, and the cost factor was enormous. Other products were fully automated, but they still required a tremendous amount of maintenance to make sure they worked properly, and that wasn’t a task we wanted to take on. Customer support was often lacking as well. When Hitachi Data Systems introduced us to InMage, we found what we were looking for.”

NCM implemented InMage Scout, a disaster recovery and business continuity software solution from Santa Clara–based InMage Systems. InMage’s unique hybrid recovery technology enables granular recovery capabilities that can meet the most stringent recovery point objectives (RPOs) and recovery time objectives (RTOs) while completely eliminating backups as a discrete operation. InMage cornerstone technologies include continuous data protection (CDP), asynchronous replication, application failover/failback and WAN optimization.

“The strategy was to replicate data from our primary site in California to our secondary site in Nevada, and be able to perform a manual recovery that met our RTO of two hours and our RPO of 30 minutes,” says Etheridge. “Most manual recovery solutions are extremely onerous – a lot of things have to happen at the same time in order for them to work properly. With InMage, we could do point-in-time recovery with application-consistent recovery points. This was a huge benefit, since we work with multi-tier applications. Whether we go back 10 minutes or to the exact same second, we know that our data and applications will come up properly.”

InMage Scout uses application-specific APIs to mark application-consistent points (referred to as AppShots) in the data stream. AppShots are most often used for recovery because they support the shortest RTOs, but InMage can reliably re-create any previous point in time, regardless of whether it is application consistent (like an AppShot) or crash consistent (any other point in the data stream).

Other advantageous features for NCM included InMage’s replication processes, bandwidth utilization and bandwidth optimization. Etheridge had previously looked at several bandwidth optimization products, but he found the learning curve and constantly changing compression ratios to be troublesome.

“The compression we get from InMage is phenomenal,” says Etheridge. “We didn’t need to spend weeks or months learning how to use it. The throttling works well, so we’ve always been able to use only a fraction of the bandwidth we thought we’d need. Instead of over 200Mbit, 50Mbit ended up working just fine for us.”

Another particularly useful feature for NCM was InMage’s sparse retention, especially when it came to compliance mandates. Sparse retention retains long-term CDP information on the disk while minimizing target storage utilization. As time progresses, the application consistency bookmarks are maintained at less frequent intervals. For example, a sparse retention policy could be specified as follows: retain all changes for the last three days, one recovery point per hour for four days beyond that, and one recovery point per day for older data. Users then have the ability to recover to application-consistent points further back in time without consuming significantly more target storage beyond the first week.

“Sarbanes-Oxley is a major mandate in our industry,” says Etheridge. “We use InMage’s sparse retention as part of our backup strategy and our primary methodology for recovering a file. Since the SEC requires seven-year retention and proof that files have not been amended during that timeframe, the simplest and easiest way to accomplish that is sparse retention. We can go back to a designated point in time, and our compliance department can quickly satisfy any requests that arise.  Sparse retention is incredibly important in meeting many of our needs, and has proved especially beneficial for SOX guidelines.”

Putting It to the Test: InMage Meets RPO/RTO Benchmarks

InMage enabled Niemann Capital Management to meet its recovery time and recovery point objectives with benefits including application-consistent and granular recoveries, bandwidth and capacity optimizations, and remote administration so additional IT personnel were not required to manage the solution.

“We recently conducted a DR test, and our failover time from the moment we stopped operations at our primary site until we were completely operational at the secondary site was 26 minutes,” says Etheridge.  That included all validation that everything was working properly and that we could perform all required functions. Our goal was for mission-critical applications to be functional within two hours, and it only took us a fourth of the time to meet that RTO. That really proved to us the value of the InMage solution. Failing back over to the primary site was also incredibly simple in a test scenario. Another thing that’s advanced about InMage is its file system-aware replication. With most products, replication is at block level. If you have large blocks and only need one tiny bit of information, that’s a lot of wasted bandwidth. With InMage’s file system-aware replication, we have cut back on bandwidth even more and really sped things up. Our RPO is 30 minutes but most of the time we end up under two minutes, which is phenomenal.”

“The product speaks for itself, but the cooperation we’ve received from InMage has also been second to none,” concludes Etheridge. “We need to know we have a partner that takes our needs seriously and makes sure trained people are available in the event of a disaster. I personally test relationships, and the one we’ve had with InMage is the best support relationship I’ve ever had. It does a lot for our confidence level. If our entire IT department was unavailable, I’m certain InMage could perform a full site recovery. The bottom line is that we have a system for a fraction of the price we would have had to pay for a more conventional method.”

Photo courtesy of MCS@Flickr

The post Niemann Capital Management Invests in a Winning Recovery Strategy With InMage appeared first on The Data Center Journal.