Blog Posts From The Data Stack Tagged With server_consolidation

Data centers: What does it take to heat things up?

webadmin@intel.com — Tue, 02 Apr 2013 15:00:25 GMT

This post originally appeared in GreenBiz on December 26, 2012

Keeping things cool has long been a mantra for data center operators, but new research suggests it may not be essential for everyone.

Data centers have historically operated at temperatures ranging between 64° and 68° Fahrenheit (or 17° to 20° Celsius), prompting them to spend approximately 44 percent of their total power budgets on cooling.

Originally, the varied mix of equipment and associated warranties dictated these relativelycool temperatures, and service level agreements (SLAs) often included explicit language about how much deviation was acceptable.

But while it's true temperature control can affect equipment reliability and appropriatemanagement and monitoring is needed for business continuity, new research supports the idea that higher temperatures are beneficial for most data centers.

So, how do you know when to raise the temperature, and by how much? Are there any changes recommended to reduce business risks?

Should every data center cut back on cooling?

When we ask, many data center managers can’t tell us why they set the thermostat at a particular temperature. It’s just the way it has been done for years.

But when well-known companies -- including Facebook, Google, Yahoo!, Korea Telecom andothers -- publicize their high temperature ambient (HTA) successes at 80°F and above, we all pay attention. And when research and on-the-ground examples support the efficacy of HTA data centers, suddenly we are all tempted to reduce our cooling costs by just pushing up the thermostat.

Before arbitrarily cutting back on cooling and letting the ambient temperature rise, however, as a data center manager, you’ll want to review your equipment warranties, SLAs and compliance requirements. For those responsible for data centers supporting legacy systems that require lower operating temperatures, or for those whose organizations are subject to extremely stringent compliance requirements, you’ll want to continue to take a very conservative approach.

HTA Best Practices

That said, today’s major vendors of data center equipment generally design and warrant systems and products for reliable operation at 40°C or 100°F. It makes economical sense to take advantage of the latest product specifications and warranties. This means considering simple as well as more involved changes:

Thermostat-only changes. Data centers potentially reduce cooling costs by 4 percent for every 1°C increase in operating temperature. (Cooling accounts for up to 44 percent of the power consumed in an un-optimized data center, which is the typical design being implemented in emerging economies.)
Retrofitting the data center. Besides raising ambient temperature, hot and cold air aisle separation drives up the savings, and replacing chillers with economizers (heat exchangers) can yield dramatic savings. In one of Intel’s data centers (with 900 production servers), retrofitting and raising the temperature to 33°C or 91.4°F has translated to a 67 percent annual power savings ($2.87 million in a 10MW data center).
Optimized data centers. Hot aisle containment, energy-efficient servers and a node-level power management solution capable of dynamic resource management (e.g., power capping servers, racks and rows; adjusting server performance and fan speeds) have been shown to dramatically drive up energy efficiency and support operation at the highest temperatures without increasing risk to the business. Real-world results show power utilization efficiencies can be increased so that IT power utilization improves from 50 percent to 81 percent of the total.

All things -- and temperatures -- in moderation

Your data center can take some steps to reap the cost benefits of HTA operation. Start with a plan to phase out, relocate or outsource any legacy system that is keeping your data center at the lower, more expensive operating temperatures. As soon as possible, bump up the temperature by one degree or two, to get on a path toward HTA.

However far along you are, an energy management solution may improve your visibility into energy use and thermal patterns within your data center. Among the foundations necessary for achieving power efficiency through HTA practices are real-time visibility and the abilities to log power and temperature data, and to analyze usage trends based on the logged data.

These same capabilities can also enable other energy management practices such as lowering carbon emissions, thus allowing you to expand a data center without exceeding power limits, and efficiently balancing services and workloads to avoid power spikes.

The cost and power savings achievable by adopting HTA as a model may well represent the new norm. The timing is perfect: Data centers currently consume 1.5 percent of all of the world’s power. Annual server energy costs exceed $27 billion. By 2014, these numbers are expected to double. Bumping up your data center’s ambient temperature directly reduces cooling costs and power consumption, and simultaneously reduces CO₂ emissions.

HTA makes business sense, and it makes sense for our planet. Get ready for the data center world to heat up!

Jeff Klaus is the director of Intel Data Center manager (DCM). Jeff leads a global team that designs, builds, sells, and supports Intel® DCM.

Stream Mind Enhances Financial Transactions across Europe

webadmin@intel.com — Sat, 02 Feb 2013 02:02:06 GMT

Download Now

Stream Mind was chosen by the largest French banks to provide software to support SEPAmail*, a new messaging network designed to efficiently and securely transfer supporting information and documentation relating to financial transactions across the Internet. To ensure its software can meet the requirements of all potential customers, from individuals to large financial organizations, Stream Mind collaborated with HP to offer a range of hardware and hosting solutions based on the Intel® Xeon® processor E5 family and HP ProLiant* Gen8 servers. By optimizing its software to take advantage of the processors’ capabilities, Stream Mind has strengthened its offering to customers ahead of the launch of SEPAmail.

“Optimizing our applications for the Intel Xeon processor E5 family and HP ProLiant Gen8 servers has enabled us to develop a higher-performing, more reliable and–crucially–cost-effective proposition," explained Nicolas Muhadri, founder and president of Stream Mind. "By supporting our offering with Intel’s technology, we can ensure the scalability of our offering, and its compatibility with our customers’ existing IT environments.”

To learn more, download our new Stream Mind business success story. You can find more like this one on Intel.com and iTunes. And to keep up to date on the latest business success stories, be sure to follow ReferenceRoom on Twitter.

*Other names and brands may be claimed as the property of others.

Enterprise IT & 2103: Some Predictions

webadmin@intel.com — Tue, 22 Jan 2013 16:28:11 GMT

IT departments will be embroiled in IT transformation from now on.
Private Clouds proliferate
IT shops are surprised at the number of corporate applications in the public cloud
MicroServers will be a bigger part of the market than 10% by EOY 13
Mission Critical will continue the steady migration to virtualized infrastructure

Prediction #1: IT departments will be embroiled in transformation because they will now have competition. Their customers will go to the public web if they can’t get support from the corporate shop. This transformation is already happening. One shop I’ve talked with is striving to provide their business unit customers with rapid deployment of virtual servers. The old way of forcing these business units to wait up to six months or more for a server are rapidly ending.

When a business unit is told they’ll have to wait, the business opportunity that they are trying to tackle might just slip away. Instead of letting that happen they’ll go to a public cloud provider and get a server in minutes. One article recently referred to this as ‘Rogue Clouds’. (See prediction #3 above!)

Of course IT shops don’t want to lose control but the proliferation of alternatives for their customers is turning all this around. IT shops have to transform. IT shops have to transform to remain relevant.

To do this they are choosing to move to a homogenous environment of low cost 2 socket servers or even MicroServers (see prediction 4 above). By having a standardized environment on which to build a highly virtualized compute farm or even private cloud (See prediction #2 above) the IT shop can provide flexibility and high availability to their customers. Again, a shop I’ve talked to is using VMware’s vSphere to provide high availability to their customers. They say that they have better availability and uptime at a much lower cost than they were getting on their AIX environment. Suddenly Mission Critical in the private cloud starts to make sense. (See prediction #5 above)

Let’s build out that AIX example. Say the AIX server is hosting 100 virtual machines in combinations of LPARS and virtual software. Let’s say that there is an unanticipated fault that brings down the entire machine. Unless these virtual machines are clustered to a virtual machine on another server, all 100 have just gone down. To bring the machine back up, the structure of the virtual machines has to be recreated followed by restarting restored images of the 100 servers. That’s going to take a while. One choice to avoid this is to purchase or lease a second AIX server to cluster as a passive high availability host. The impact to the corporation could be hours of outage or costs in the 7 to 8 figures for the clustered solution.

Another choice to port the applications to a virtual server in a private cloud where high availability can be selected as a configuration option while instantiating the server. If the host server happens to fail then the server is instantiated on another identical server immediately; no need to await configuration of the server. The net impact to the corporation is possibly a second or so of outage. The cost of the 2 socket server isn’t very high and replacing it in the rack is a choice as having spare servers isn’t an expensive proposition. And now with server disaggregation (yes, Intel is a collaborator) the task of configuring server farms is becoming simpler than assembling a model using toy blocks.

The role of IT is rapidly changing. The role of the IT staff is changing. The role of the server is changing. The architecture of different brands of servers is losing any distinction. The change is occurring at an ever rapid rate. The only thing we in IT can be assured of is that the ground under our feet is shifting and flexibility is a guiding principle for our careers.

Follow me on Twitter @WallySP for more!

Solid State Drives Ramp Up Performance for In-Memory Databases

tim.allen@intel.com — Wed, 26 Dec 2012 15:40:27 GMT

Data intensive computing takes muscle – and not just in the form of more powerful processors. Revving up performance for time-sensitive, transactional analytics, takes a more complete package, which includes in-system memory database software plus low latency storage solutions. Watch this video to learn how adding solid-state storage drives can greatly reduce process persistent data bottlenecks and speed database performance.

Not so long ago, enterprise-level relational databases consisted of two segments: a large server that ran the database software and a separate, usually detached storage environment with traditional disk drives. However, for time-sensitive processing, the latency lag that occurred as data passed between the two segments became a real drag on performance.

Today’s database environments have become much more complex, but they still suffer from latency whenever data-flows are processed to a spinning hard drive.

In the past couple of decades, processor efficiency and speeds have increased as much as 50,000 times. Over the same period, hard drive performance, based on the speed of a spinning cylinder, has improved only 30 to 40 percent. Rotating media storage becomes the real bottleneck if you’re looking to pump out real-time analytics.

One way to optimize transactional performance is by integrating in-memory database solutions, such as the Oracle TimesTen* In-Memory Database, a relational database that runs purely in system memory to increase both speed and reliability.

However, while the Oracle TimesTen database solution runs only on in-system memory, it still requires logging transactions to some form of persistent storage. If this happens to be standard rotating media, then you’re back to having a hard drive latency issue.

The answer: Add solid-state storage to your database environment. The above video demonstration shows how Intel^® Solid-State Drives (Intel^® SSD) can help organizations get the full value out of their Oracle TimesTen investments and better manage real-time data by removing storage bottlenecks that build up when your systems are dependent on standard hard disk drives.

Follow me on Twitter: @TimIntel

The 12 Days of Christmas in the Data Center

webadmin@intel.com — Sat, 22 Dec 2012 15:00:46 GMT

This post originally appeared in Data Center Knowledge on December 21st, 2012.

Jeffrey S. Klaus is the Director of Data Center Solutions at Intel Corporation, where he has managed various groups for more than 12 years. Klaus’s team is pioneering data center power and thermal management solutions, which are sold through an ecosystem of data center infrastructure management (DCIM) software and hardware companies around the world.

Another year’s end, and we’re in the midst of another holiday season. Besides anticipating time off, family celebrations, and gift giving, every IT professional should be anticipating—and planning for—the challenges relating to data center energy management in 2013.

On the First Day of Data Center Christmas: IT Transformation

The data center has moved from a support business to a mission-critical resource. Next year, I could argue that the data center will become the most-critical resource. The elevation of the data center is being driven by demands for transaction speed and exploding numbers of devices and applications used for sales, service, operations, HR, and practically every functional area. Business users will continue to expect more from the data center. They want to improve their productivity with increasingly self-service capabilities, customization, on-demand services, and, above all, reliability that translates to highly available data center services.

Second Day: Organizational Disconnects

Historically, the various IT and facilities teams worked separately. Rarely did hardware, software, networking, and facilities teams come together, and if they did, they rarely understood each other. The 2013 outlook, with escalating energy costs and a continued sluggish global economy, calls for increasing focus on power optimization, and that means providing tools that not only work for all of the various teams, but encourage cooperation among the teams.

Third Day: Affordability of Servers and Storage Drives Up Demand

Dramatic server/storage price reductions over the last decade have led to mass migrations of tasks to online and automated platforms, thus driving up energy consumption in the data center. Power and cooling have become significant portions of the budget; some argue power has become the single biggest expense.

Fourth, Fifth and Sixth Days: Virtualization, Clouds, and Mobility Change Energy Profiles

Rapid change is nothing new in the data center, but 2013 will see several major technology trends gaining wide-scale acceptance. Virtualization is expanding from servers into desktop infrastructure, and users are demanding the flexibility and rapid provisioning that is only possible within a private or public cloud environment. Mobility adds another layer of complexity, as employees bring their own smart devices to work, thus driving up network traffic and server workloads with apps and anytime, anywhere access to data center resources. The data center is being bombarded with service requests, and large companies are already hitting the power restrictions of their facilities as well as the limits of some local utility companies to meet their needs.

Seventh Day: Natural Disaster Preparedness

The 2011 earthquake and tsunami in Japan and this year’s hurricane season that included Sandy’s devastation of New York and surrounding states are vivid reminders that every data center should be continually refining its disaster plans. The 2013 challenge will be to ensure that disaster plans include prolonging operation with backup power supplies. Disaster recovery should be elevated to a data center best practice, supported by a management solution that offers on-the-fly server adjustments to minimize power draw.

Eighth Day: Battling Methodologies and Tools

Natural disasters are one of the driving forces fueling growth of co-location (colo) facilities. Since many colo companies position their services as insurance for any power outage situation, some are among the early adopters of intelligent energy management solutions. Others have developed their own power management tools, and these will increasingly impact off-the-shelf DCIM solutions.

Ninth Day: The Search for Holistic DCIM Solutions

The ongoing debates about energy management approaches are driving the demand for and evolution of holistic DCIM platforms. Data center teams should look for solutions based on real-time data collection versus less-accurate predictive models. With fine-grained thermal and power monitoring, a DCIM solution should enable a data collection that feeds into holistic analysis and ultimately control of energy behaviors.

Tenth Day: Budget-Restricted Technology Roll-Outs

Of course, even the best solution doesn’t automatically override the budget restrictions stemming from global economic uncertainty. Therefore, data center managers will likely aim for smaller-scale trials and proofs of concepts than originally planned. A phased-in deployment should still be designed to achieve the same results over the long term, with each phase essentially self-funding the next phase with the proven gains in energy efficiency.

Eleventh Day: Vendor Consolidation

DCIM will continue to mature and, along with economic pressures, the rapid rate of change may likely lead to vendor consolidation. This will include large vendors buying up smaller tool vendors, to accelerate the development of their platforms. Maturation ultimately benefits the customer, however, and so the challenge here will be to avoid investments in solutions that may get swallowed up by competitors.

Twelfth Day: Inability to Predict the Future

As the year comes to a close, we are left with many unknowns about the DCIM market and how energy management in the data center will look a year from now. How will the market size compare to the 2013-2014 predictions? What will it take to move the technology to the next level?

We will all be watching and analyzing market movements, but ultimately data center demand will drive the technology. And this demand is growing at a healthy pace. Slow economy or not, energy costs are not going to suddenly plummet. More likely, energy demand will drive up prices, and governments will continue to increase energy taxes. DCIM solutions that build in proactive, fine-grained energy management capabilities are the best—and perhaps only—way to keep the data center sufficiently supplied without breaking the budget.

Follow Intel DCM: https://twitter.com/IntelDCM

FinArch and Gwinnett Increase Competitiveness and Manage Volumes of Data with Intel® Xeon® Processor E5 Family

webadmin@intel.com — Fri, 14 Dec 2012 18:26:28 GMT

Servers, workstations, and storage solutions based on the Intel® Xeon® processor E5 family deliver the performance, built-in capabilities, and cost-effectiveness to make data centers flexible and efficient. Learn how companies are putting it to work in two new business success stories:

FinArch Increases Financial Analysis Competitiveness: Staying true to its commitment to delivering integrated finance and risk solutions, FinArch created Financial Studio* (FinStudio*). FinStudio was deployed on NOVATTE’s CloudBee* servers utilizing the Intel Xeon processor E5-2600 series, enhancing performance, I/O, and energy efficiency in financial reporting.
Gwinnett Medical Center Manages a Data Explosion: A healthcare leader handles big data workloads with a private cloud powered by Intel® data center technologies.

Find more business success stories like these on Intel.com and iTunes. And to keep up to date on the latest business success stories, be sure to follow ReferenceRoom on Twitter.

*Other names and brands may be claimed as the property of others.

Modernize Your Mission Critical Systems - Webinar Dec. 18th

webadmin@intel.com — Wed, 12 Dec 2012 16:45:01 GMT

I'm one of the featured speakers on this webinar. I'd sure like you to join me and ask questions.

Get expert insight for modernizing your mission-critical IT environment

Intel® IT Center Talk to an Expert webinar series:
Tuesday, December 18, 2012
10 a.m. Pacific standard time

Keeping the most important workloads running 24-7 can keep IT managers up at night. It is also essential to be able to rapidly analyze the ever-increasing amounts of data being generated every day. Increasingly, these challenges need to be met in a tight budgetary environment.

You’re faced with a strategic choice: Continue to try to meet these growing demands with legacy infrastructure, or migrate your mission-critical deployments to an open-standards-based environment built upon Intel® Xeon® processor-based solutions.

Join me and our panel of experts to learn a proven approach to modernization. Topics include:

Trends and market data related to mission-critical application modernization and a perspective on the updated solution stack
Strategic options to address the current software, hardware, and business challenges in your mission-critical environment
Practical steps for your mission-critical migration projects, including which workloads to transition first, and ways to divide the project into manageable pieces
Lessons learned in modernizing mission-critical environments, based on a rich history of innovation and global experience from IBM and Intel

CIOs Reduce Data Center Costs Through Power and Cooling Efficiency

webadmin@intel.com — Sun, 11 Nov 2012 15:03:22 GMT

Energy costs are the fastest-rising cost element in the data center. Based on recent trends, the EPA estimates that energy consumed by data centers will continue to grow by 12 percent per year. As the director of Intel’s Data Center Manager (DCM) group, I and my team have observed how the data center is now a source for CIOs and their technical teams to add to the bottom line through increased power and cooling efficiency.

In fact, we’ve found three value drivers for power and cooling efficiency: measuring energy use; increasing energy efficiency; and power capacity planning.

In an article I wrote earlier this year for Information Technology (IT) Business Edge, I examine how each of these three drivers can help CIOs to optimize efficiencies and begin to control their rapidly escalating data center costs, to turn this cost center into an opportunity to contribute to the bottom line. To read the blog in its entirety, please check it out on IT Business Edge.

Provided by QuinStreet, Inc; Intel DCM Director Jeff Klaus published the Guest Opinion, “CIOs Reduce Data Center Costs Through Power and Cooling Efficiency” on ITBusinessEdge on Feb. 1, 2012.

What’s in a Name: Converged Network Adapters

webadmin@intel.com — Fri, 05 Oct 2012 15:00:24 GMT

Several months ago, our flagship 10 Gigabit Ethernet (10GbE) server adapters underwent a big change. We retired the Intel® Ethernet 10 Gigabit Server Adapter family name and replaced it with Intel® Ethernet 10 Gigabit Converged Network Adapter family. The adapters themselves didn’t change a bit; they’re the same reliable products that have led us to the top spot among 10GbE adapter suppliers[1].

Why did we rename such a successful product line? Quite simply, Converged Network Adapter (CNA) is a much more accurate description of our 10GbE adapters and the features they offer. As IT organizations upgrade their data center networks, we want to make sure they know that these Intel Ethernet adapters meet not only their Ethernet networking needs, but also their converged networking needs.

For you non-networking folks, a CNA is a 10GbE adapter that supports standard LAN traffic as well as Fibre Channel over Ethernet (FCoE) traffic and iSCSI traffic. Traditional LANs and Fibre Channel (FC) storage area networks (SANs) use completely separate network infrastructures, requiring storage-specific network adapters, switches, and cabling. Converged or unified networks allow LAN and SAN traffic to use or even share a 10GbE fabric, greatly simplifying the infrastructure. CNAs connect servers to these converged networks and eliminate the need for separate, dedicated storage network adapters.

So with all of these great benefits, why didn’t call our adapters CNAs from the start? Answering that one requires a history lesson.

Work on the FCoE standard began in 2007, and the first CNAs appeared several months later. For these early designs, the traditional storage adapter vendors modified their FC host bus adapter (HBA) designs to include the Intel^® 82598 10 Gigabit Ethernet Controller alongside their proprietary FC processors. With the FCoE standard still in draft form and a thin ecosystem, these first-generation adapters were little more than proof of concept vehicles.

Meanwhile, we at Intel were working to enable FCoE on the Intel 82598 10 Gigabit Ethernet Controller – the same controller that provided the Ethernet functionality for those early CNAs. We realized, however, that enabling FCoE on that controller (and adapters based on it) would require releasing our own FCoE software stack. Introducing yet another proprietary FCoE solution into the market would have made life harder for IT, and that’s the last thing we wanted to do. So we launched our new adapters as 10GbE adapters, not CNAs, and set about making FCoE easier for IT to deploy.

In 2008, Intel founded the Open FCoE project and released our FCoE initiator code to the open source community. Our goal was to get the Open FCoE initiator integrated into the Linux* kernel and help accelerate the adoption of FCoE. Any adapter vendor could use that native support to develop a CNA, giving customers more hardware options and allowing them to use a common set of OS-based management tools. The industry had gone through a similar process with the successful integration of iSCSI, another storage protocol, in every major OS and hypervisor.

In March 2009, after modifications from the Linux community, the Open FCoE initiator was integrated into version 2.6.29 of the Linux kernel and soon found its way into major distributions, including Red Hat and SLES.

In early 2011, we announced that our newest 10 Gigabit Controller, the Intel® 82599 10 Gigabit Ethernet Controller and the integrated FCoE initiators in Linux and Windows had been qualified by EMC, Cisco, and NetApp. The Intel® Ethernet Server Adapter X520 family, which is powered by the Intel 82599 10 Gigabit Ethernet Controller, was included in this announcement.

And in August 2011, VMware announced Open FCoE integration as part of the vSphere 5.0 launch. With that launch, the Intel Ethernet Server Adapter X520 and Intel 82599 10 Gigabit Ethernet Controller had FCoE support in every major operating system and hypervisor. We felt it was important for customers to understand that Intel Ethernet 10 Gigabit Server Adapters were full CNAs, so later that year, we decided to rename them, and the Intel Ethernet Converged Network Adapter family was born.

Our 10GbE CNAs are the industry’s top-selling 10GbE adapters. Earlier this year, we expanded the family by adding the Intel® Ethernet Converged Network Adapter X540, our fourth-generation 10GBASE-T adapter. Through our Open FCoE efforts, we have given the industry another option for enabling FCoE – an option that doesn’t depend on proprietary hardware and software, can use standard OS-based tools, and scales with advancements in server architectures.

It has been a long journey getting to this point, but sometimes it takes time to do things right.

If you’d like to learn more about the advantages of Open-FCoE-based solutions, check out this blog post on Open FCoE in VMware vSphere.

[1] Crehan Research, Server-class Adapter and LOM, 2Q12

Moody's Invests in a Scalable Infrastructure

webadmin@intel.com — Sat, 11 Aug 2012 00:33:46 GMT

Download Now

The credit ratings, research, and risk analysis provides by Moody’s Investors Service play a crucial role in helping investors navigate the quickly changing waters of financial markets. To improve the efficiency and scalability of the infrastructure used for mission-critical ratings and analysis applications, the IT group decided to migrate workloads from proprietary to Linux* environments running on Intel® Xeon® processors. By adopting Intel Xeon processors and open-source products, the company is achieving better performance, gaining more cost-effective scalability, and reducing costs.

“There has been much greater innovation among x86 platform vendors and in the open-source community than among proprietary platform vendors,” explained Brian Clark, CTO of Moody’s. “It was clear that we could achieve better price/performance and scalability by moving to a Linux environment running on Intel Xeon processors.”

For the whole story, download our new Moody’s business success story. You can find more business success stories like this one on Intel.com and iTunes. And to keep up to date on the latest business success stories, be sure to follow ReferenceRoom on Twitter.

*Other names and brands may be claimed as the property of others.

Re-thinking high-availability

webadmin@intel.com — Mon, 18 Jun 2012 14:17:18 GMT

Virtualization and Cloud computing brought new approaches on computer architecture organization and Data Center operation, so I believe that a brief review on key availability concepts and how these apply for cloud computing is worth re-thinking. Are old strategies adopted years ago still valid nowadays?

Usually, availability is measured by a combination of tow metrics:

MTBF – Mean Time between Failures

MTTR – Maximum Time to Repair

It describes the number of system failures in a period of time and how long, on average; it takes to be get back online. Using these two metrics, the overall availability is given by this formula:

Where D is availability (e.g. 99.997%)

So, in order to think on availability we must treat this concept in layers as part of the system organization, usually we slice the strategy into 5 layers:

Electronic Components: It’s the first layer and basically is elementary components of hardware from MTBF perspective, i.e. quality and endurance of hard-disks, memory, CPUs, power supply, etc.
Data Protection: Mechanism and algorithms embedded in hardware architecture that guarantee data coherency, consistency and integrity flowing through components, such as value generated by CPU, stored into cache and coherency with neighbour caches, memory and capacity to recover from bit-flip, and disk integrity and durability;
Component Redundancy: In order to avoid that a failure in a hardware component can compromise the system, adoption of redundancy lower MTBF components can improve availability of entire system such as: redundant power supply, RAID configuration for hard-disks, redundant NIC, memory sparing technology, etc.
Server Redundancy: Redundancy of entire server with appropriate technology based on systems: Failover cluster for scale-up applications or load balancers for scale-out applications in order to make the environment more reliable on case of a server failure;
Disaster Recovery: Assuming that a major disaster can happen, this layer of availability is designed to address Data Center disaster or even a documented procedure to restore the entire system.

Actually, with virtualization at the base of cloud computing strategies that embed failover capabilities and scalability provided by sharing compute resources, server redundancy becomes a granted feature in a cloud infrastructure.

If you look at each layer of availability, you will find that for most enterprise-class servers, components used to assemble the machine already possess a high MTBF without extra costs. Thanks to manufacture process improvements and scaling computer industry. While basic security is present at the CPU and memory level, anything more advanced or any redundancy will add to the bottom line cost.

Let’s take a moment and re-think the approach. If you have a stateless application you will only lose the active session in the failing machine but the application itself is still available. And for stateful applications you wont just lose the active but be penalized on the MTTR, which is something predictable, you can work around. The time to boot the guest machines and services on one of the remaining servers in the pool could be a fair approach with a revert investment in RAS on more servers in order to provide a better response time. And as a bonus you can use the extra machines for peak demand when necessary to ease your budget.

It’s for these reasons that some manufactures are shipping machines sharing components instead of putting in redundant configuration, such as a twin server sharing the same power supply, blade servers that share I/O from enclosure, etc.

Sometimes, we have to review our values in order to keep competitive, I’m pretty sure, if seven years ago, predicting this kind of demand and ways to archive better availably with lower CAPEx would be considered insane… It might be time to rethink your strategy.

Best Regards!

Cisco Live! 2012: Big Things are Afoot for 10GBASE-T

webadmin@intel.com — Wed, 13 Jun 2012 15:00:17 GMT

The Summer IT industry event season has kicked into high gear, and this week I’m at Cisco Live! 2012 in San Diego. Networking products and technologies are, of course, one of the primary focus areas of the show, so it’s no surprise that Cisco’s announcement earlier this week included a number of new networking products. One particularly significant product is the Nexus 5596T switch, a new data center switch and the first 10GBASE-T member of the Nexus 5000 family.

If you’ve read some of my previous posts, you know that 10GBASE-T is 10 Gigabit Ethernet over twisted-pair copper cabling – the stuff that’s installed in nearly every data center today – and that it uses the familiar RJ-45 connector. 10GBASE-T has been a big topic for us here at Intel, especially with the launch of the Intel® Ethernet Controller X540 in March.

Need proof? Here’s a word cloud of my posts for the last year. Other than the common words like “Intel,” “Ethernet,” and “10GbE,” the term I used the most was “10GBASE-T.” See it there on the left?

But I digress. (And I drop in the occasional overused phrase.)

Kaartik Viswanath, product manager for the Nexus 5000 family, was kind enough to take a few minutes to answer some questions about the new switch and Cisco’s views on 10GBASE-T.

BY: Kaartik, thanks for taking the time to answer a few questions today. Tell me about the Nexus 5596T switch and 10GBASE-T module that Cisco announced yesterday.

KV: Sure. We’re very excited about the new Nexus 5596T switch. It’s the first 10GBASE-T member of the Nexus 5000 family, and it’s coming at the perfect time, with 10GBASE-T LOM (LAN on motherboard) connections now being integrated onto mainstream server motherboards. LOM integration will help drive 10GbE adoption, and all those new 10GBASE-T ports need a high-performance, high-port-density switch to connect to. The Nexus 5596T has 32 fixed 10GBASE-T ports, and through the addition of the new 12-port 10GBASE-T Cisco Generic Expansion Module (GEM), it can support up to 68 total 10GBASE-T ports in a two-RU (rack unit) design. Plus, customers can deploy any of the existing GEMs in any of the Nexus 5596T’s three GEM slots.

The Nexus 5596T also includes 16 fixed SFP+ ports, which customers can use to connect to aggregation switches, servers, or Nexus 2000 Fabric Extenders using optical fiber or direct attach copper connections. With the Nexus 5596T switch, our customers have the flexibility to deploy both 1/10GBASE-T Ethernet on Copper and FC/FCoE/Ethernet on SFP+ ports on the same chassis.

BY: Are you hearing a lot of interest in 10GBASE-T from your customers?

KV: Yes, definitely, and I think there are a couple of major reasons for that. First, 10GBASE-T offers the easiest path for folks looking to migrate from One Gigabit Ethernet (GbE). 10GBASE-T uses the same twisted-pair copper cabling and RJ-45 connectors as existing GbE networks, and it’s backwards-compatible with all the 1000BASE-T products out there today. That means you can replace your existing 1000BASE-T switch with a Nexus 5596T and connect to both 10GBASE-T and 1000BASE-T server connections. And as you’re ready, you can upgrade servers to 10GBASE-T.

I think the other big reason 10GBASE-T is so appealing is the deployment flexibility it offers; 100 meters of reach is sufficient for the vast majority of data center deployments, whether it’s top-of-rack, middle-of-row, or end-of-row. Plus, twisted-pair copper cabling is much more cost-effective than the fiber or direct-attach copper cabling that’s used in the majority of 10GbE deployments today.

BY: Cisco and Intel both support multiple 10GbE interfaces in their products. How do you see 10GBASE-T fitting into the mix?

KV: We’ll support whichever interfaces our customers want to use. However, there are some general guidelines that most folks seem to be following. For longer distances – over 100 meters – SFP+ optical connections are really the only choice, given their longer reach. But fiber costs really don’t lend themselves to broad deployment. Today, most 10GbE deployments use the top of rack model, where servers connect to an in-rack switch using SFP+ direct attach copper (DAC) connections. DAC reach is only seven meters, but that’s plenty for any intra-rack connections.

10GBASE-T hits sort of a sweet spot because of its distance capabilities. It can connect switches to servers in top of rack deployments, with cables that are less expensive than SFP+ DAC, or it can be used for the longer runs where fiber is being used today – up to 100 meters, of course.

There are cases where SFP+ has some advantages, particularly for latency-sensitive applications or if the customers are sensitive to power consumption, but when it comes to deployment flexibility, costs, and ease of implementation, 10GBASE-T is well-positioned as the interface of choice for broad adoption.

BY: How about Fibre Channel over Ethernet? Does the Nexus 5596T switch support FCoE over 10GBASE-T?

KV: Great question. FCoE is a key ingredient in Cisco’s unified fabric vision, and it’s supported in our 10 Gigabit Nexus and UCS product lines. The Nexus 5596T hardware is FCoE-capable like all of our Nexus 5000 switches, and we’re working on FCoE characterization in our labs. We’ve been working closely with Intel to verify FCoE interoperability with the Intel Ethernet Controller X540.

There’s been a fair amount of discussion in the industry around whether 10GBASE-T is a suitable fabric for FCoE. Our collaboration with our ecosystem partners, including Intel, network cable vendors, and storage vendors, will help ensure there aren’t any issues before we enable the feature on the Nexus 5596T. Assuming everything goes well, we’ll also enable FCoE over 10GBASE-T in our 12-port 10GBASE-T GEM Module as well as our fabric extender line with the upcoming Nexus 2232TM-E Fabric Extender.

BY: Kaartik, a couple of quick final questions for you. Before you joined the Nexus team, you worked on the campus network side of Cisco, correct?

KV: Yes, that’s right. I was the Product Manager in the Unified Access Business Unit, managing the Fixed 10/100 business.

BY: How is the data center networking world different than the campus networking world?

KV: One thing that stands out is the faster speeds of the interconnects in data center switching products. In campus networks, the vast majority of connections are at Gigabit or Fast Ethernet (100Mbps) speeds. Our Nexus product line, by contrast, has switches with 96 10 Gigabit ports and 40 Gigabit and 100 Gigabit uplinks. So the speed of individual links is greater, but a campus network typically connects many more machines than a data center network, as there are more client PCs than there are servers.

Another big difference is the technologies that are supported in each class of product. There’s certainly some overlap, but technologies like Fibre Channel over Ethernet, Data Center Bridging, I/O virtualization – those are mostly confined to the data center world. Similarly, technologies like Power over Ethernet Plus and Universal Power over Ethernet today are more prevalent in campus access type of deployments and are not so common in the data center world.

BY: Thanks for taking the time to chat today, Kaartik. We’re looking forward to continuing our work with Cisco.

KV: No problem. I’m looking forward to it, too.

We at Intel have been talking about 10GBASE-T for a long time now, and it’s great to see the ecosystem continuing to grow with new products like the Nexus 5596T switch. I’d like to thank Kaartik for taking the time to answer these questions for us.

For the latest, follow us on Twitter: @IntelEthernet.

Mercator Ocean Gets More Computing Power

webadmin@intel.com — Sat, 19 May 2012 00:15:36 GMT

Download Now

Mercator Ocean wanted an R&D computing system that would let it conduct high-resolution simulations while reducing costs and enhancing performance. It deployed Dell PowerEdge* servers with Intel® Xeon® processors to deliver the highest performance for code simulating the complexities of the physical state of the world’s oceans.

Performance rose around 600 percent due to increased server density and enhanced processing power. Total cost of ownership went down because of lower power and coding costs.

“We’ve greatly increased processing power and performance while significantly reducing power and cooling costs,” explained Bertrand Ferret, head Mercator Ocean’s IT department.

To learn more, download the new Mercator Ocean business success story. As always, you can find many more like this one on the Intel.com Business Success Stories for IT Managers page or the Business Success Stories for IT Managers channel on iTunes. And to keep up to date on the latest business success stories, follow ReferenceRoom on Twitter.

*Other names and brands may be claimed as the property of others.

Database Performance & Real World Questions

webadmin@intel.com — Tue, 24 Apr 2012 13:32:16 GMT

I get questions occasionally from customers.

One recently was, ‘Can Intel Xeon Processors handle a 20TB Oracle database?’

We get this question occasionally and the question doesn’t make any sense to me. I understand the basis of the question; the customer is concerned that Xeon can tackle a very large database. Is the question really, ‘Can Xeon read in a lot of data and processes it efficiently and quickly?’ We can easily show that the Xeon E7 family of processors can do this faster in benchmark tests than most proprietary RISC processors.

Higher is better

Where the question falls apart is in the premise, can a 64-bit Xeon address 20TB? If a 64-bit RISC processor can address 20TB, then a 64-bit Xeon will as well. No database is going to be read 20TB of data at a time and besides, an Oracle database is going to have a lot of space that is either empty or not used. (For instance is there really 20TB of data or is it really 12TB or less?) But the concern of the customer usually goes deeper. So let’s break this issue down.

What is the number of users? This is a useful question. For instance is it a data warehouse with only a handful of users? Or is it a highly transactional database with thousands of users? In either scenario Xeon is great. (In 2008 and 2009 I was a DBA for Oracle on a benchmark they were running of a 10TB medical database with between 10 and 20 thousand of users. The Xeon processors for this benchmark were a number of generations ago.)

Another question that is maybe being asked is: ‘What is the largest data file I can create for my 20TB database?’ What I’ve found behind this question is a concern regarding the manageability of the database given the number of datafiles that would need to be created to get to 20TB. (For that benchmark 3 years ago it took me all weekend to build a 10TB database with 1GB datafiles. I had them spread out but there were an awful lot of them. Today, with much faster I/O creating a 20TB database will be much faster.)

Another concern being raised by the original question would be memory addressability. For large databases the thinking is that the datasets being processed in memory are very large. Can Xeon address as much memory as a proprietary RISC processor? In other words, can Xeon scale up? Do the platforms sporting a Xeon e7 processor have the memory capacity as servers with a proprietary RISC processor? We can easily demonstrate that Xeon will fill the bill by platform diversity from various vendords that can support 2TB to 6TB of RAM.

Another concern raised by the question might be on concurrent processing. With a 20TB database a lot of the processing may utilize Oracle’s parallel query function. The Xeon E7 family with its multiple core and hyper-threading technologies can easily handle significant parallel processing. For example, I started running Oracle Parallel Query Option, PQO, in 1996 when the feature first came out and I was using a 24 processor Sequent server utilizing Pentium processors.

I imagine there are additional ways to break this question down but overall the question: "Can the Xeon E7 processor run a 20TB database?" deserves an answer that addresses the real issues. The simple answer is a resounding YES!

Castilla-La Mancha Enhances Services while Saving Costs with Intel and Cisco

webadmin@intel.com — Fri, 20 Apr 2012 23:32:16 GMT

Download Now

The Spanish province of Castilla-La Mancha was eager to enhance the services it offered to local citizens, even with a tightening budget. This meant carefully planning any new resource investments for maximum return. Although the province's population is widely spread out, 95 percent have access to broadband Internet, so the regional government decided to focus on developing its online capabilities to both enhance the quality of service and reduce operating costs.

The solution was a shared cloud platform built on a virtual computing environment (VCE) from Intel, Cisco, and others. The consolidated architecture included 16 Cisco B200 M2* blade servers powered by two Intel® Xeon® processors 5650, each supporting 70 virtual machines. The virtualization-friendly features of Intel® technology optimized the performance of the new system in real time.

“Having industry experts from both Intel and Cisco on hand to share their expertise and consultancy was tremendously helpful,” said Pedro-Jesus Rodriguez Gonzalez, head of IT and Internet for Castilla-La Mancha.

For all the details, download our new Castilla-La Mancha business success story. As always, you can find many more like this on the Intel.com Business Success Stories for IT Managers page or the Business Success Stories for IT Managers channel on iTunes. And to keep up to date on the latest business success stories, follow ReferenceRoom on Twitter.

*Other names and brands may be claimed as the property of others.