The Server Room Blog

Your server workloads may be cheating you on power... get it back!

todd.christ@intel.com — Fri, 06 Nov 2009 20:12:17 GMT

Prior to the Intel Xeon X5500 Server Platforms*, measuring server power was done via expensive equipment and could only be performed in a discrete fashion. Unless you had tons of monitoring equipment to mash-up your power data - it was a tedious process. Now, using Intel DCM and Node Manager - you can pull multiple servers worth of power info to make some important power decisions in your datacenter.

First of all, you need to baseline your workload. If you're confident that you can replicate workload patterns then you've got a starting point. Otherwise, it's usually a good idea to start monitoring and looking for some cyclical patterns and/or common data points (time, power, thermals, etc) to keep track of.

In this scenario (like in my last blog) we're using a SQL workload which can be modified to run the CPU at high levels for a relatively set amount of time. The base workload runs for 7 min 30 seconds, as shown in the Intel DCM screencap below.

In this test case: Idle power for the 4 servers is 782W, and under load - the power increases to 1174W - which is a delta of 392W. This power increase occurs when work is given to the server and the P/T states react to the workload and increase power/voltage to the system to increase performance. Exactly what we've been used to seeing even since EIST was introduced several years ago.

Now, what I'll show you is something that may be very interesting in scale... I will power cap the servers by 20W each, and set the Intel DCM Power Policy to only allow 1095W for the 4 servers in the rack.

What is awesome here is that we can still finish the workload in the same 7 minutes 30 seconds. So essentially, we have saved 80W of power for each set of 4 servers and still get the same amount of work completed! In a large datacenter this can be HUGE in energy savings.

Let's do some quick math: 20W power savings per serer x 10,000 servers = 20kW power savings and you still get the work done. I hope I just helped some of you server admins get some new ideas on your next "I need a raise" talk with your manager

*your mileage may vary, so test your own workloads and report out!

Germany, France, or the UK: Who Wins for Server ROI?

edward.g.groden@intel.com — Thu, 05 Nov 2009 19:41:28 GMT

Most of the time, server ROI is measured on the data center scale, replacing tens, hundreds, or even thousands of servers with fewer higher-performing and more energy efficient servers.

But...have you ever wondered how much power you could save if you replaced every 4 year old server in an entire country with Xeon 5500 Nehalem-based systems? What about how much CO2 that could be removed for those same 4-year old servers – and number of cars it effectively removes from the road?

Well, wonder no more! Check out this short paper for an eye-opening comparison of the UK, Germany, and France, and how big of an ROI they can realize if the entire country refreshed ALL of their 4-year-old servers. It looks at power savings, land reclamation, and monetary savings in slightly different terms, like how much space can be saved in comparison to the floor area of Notre Dame Cathedral? You’ll need to read on to find out more… J

Additionally, all calculations were done using the Xeon ROI tool, so check it out and come up with some more interesting comparisons based on your city, state, or country data. Be sure to post them here!

Intel Cloud Builder

billy.cox@intel.com — Fri, 30 Oct 2009 20:50:58 GMT

For those of you implementing the infrastructure of a cloud, often called IaaS or Infrastructure as a Service, one of the challenges can be “where to start?”. With the myriad of hw options and variety of software solutions finding a starting point can be daunting.

For example:

· What server configurations are optimal?

· How to structure the network?

· What is the optimal storage configuration?

· I really don't want to write this software , therefore, what is the cloud management stack that best suits my needs?

Assuming that cost reduction and/or agility are the reasons you are building a cloud (true for the vast majority of customers), then there is huge benefit from using a largely homogenous architecture: identical server, network, storage, and management configurations across the cloud implementation. This architecture addresses the maintenance aspects of the infrastructure (remove from service if it fails, replace when enough are out of service to justify a visit to the data center) as well as the operational aspect (no special cases). Getting to the point where workloads can be hosted in this environment requires effort but has a fairly quick payback once you complete the transition.

Even with this in mind, you still have to design the hardware infrastructure and then select a set of management tools.

Intel recognizes this need and has formed the Intel Cloud Builder program to help in this ‘getting started’ phase. If you are already well down the road to building a cloud, you will likely find the output from this program useful to understand the options available in the market.

Intel(r) Cloud Builder is a fairly simple program with a powerful output:

* using a defined hardware blueprint,

* using a cloud management software stack,

* run the combination on a Intel hosted cloud test bed,

* and document the results.

For more information, please go to http://communities.intel.com/docs/DOC-4292;jsessionid=E0A2B15960F2DE39E35ADBA129D18F77.node5COMS

Billy Cox

Director, Cloud Strategy

Intel Software and Services

Migrating, there has never been a better time than now!

julie.a.baker@intel.com — Thu, 29 Oct 2009 17:47:36 GMT

Why migrate? Why now?

There has never been a better time to migrate your proprietary RISC servers running UNIX(R) to Intel(R) Xeon(R) processor-powered Dell™ PowerEdge™ servers running Red Hat(R) Enterprise Linux(R) Why? Four compelling reasons. First, cost, cost, and cost again. This industry-standard platform can reduce your capital expenditures as well as your operational costs for a lower total cost of ownership (TCO). Second, choice and flexibility. Because you’re not locked into proprietary technologies, you have substantial choices that keep you nimble and agile no matter how your business needs evolve. Third, simplicity. The Red Hat-Dell-Intel platform just works. And acquiring all the products and services you need from one source–Dell–reduces the complexities of both technology procurement and support. Finally, performance. In these challenging economic times, migrating from RISC and UNIX to a Red Hat-Dell-Intel solution is an easy and fast way to accomplish more with less, bringing true value to your business.

Power Your Enterprise

Because Red Hat Enterprise Linux is optimized for the Intel Xeon processor on which Dell PowerEdge servers are based, you can support your business’s most demanding challenges. For starters, Red Hat Enterprise Linux 5.3 takes advantage of the Intel Xeon processor 5500 series to deliver more than twice the performance compared toprevious generation Intel processors.1 Because Red Hat Enterprise Linux incorporates Intel’s energy efficiency enhancements, such as integrated power gates and automated low power states to support low-latency changes among power states, you can lower power consumption during off-peak times. This has the additional benefit of reducing datacenter cooling requirements. You achieve previously unattainable scalability with support for up to 255 central processing units (CPUs) and one terabyte of memory. And Red Hat Enterprise Linux supports Intel Hyper-Treading Technology to enable advanced parallel computing.

Learn More

To learn more about migrating from a proprietary RISC /UNIX platform to a Red Hat, Dell, Intel solution navigate to http://www.redhat.com/intelligence/, then click on White Papers.

You May be Attacking Someone, Thanks to Botnets

james.j.greene@intel.com — Wed, 28 Oct 2009 15:04:59 GMT

Do you ever wonder where Spam comes from? I have no idea where the meat-like version of Spam comes from (nor do I wish to ponder that mystery). But it is pretty well established that a huge component of the e-mail and IM Spam that we all know and hate is generated by automated programs (bots) installed on thousands or even millions of unsuspecting systems. These bots are remotely controlled via command-and-control or even peer-to-peer networks (botnets) to do the bidding of the bot developer—such as propagate Spam or other malicious software or generate denial of service attacks against designated targets. And all of this could happen without most people even knowing their system is doing anything.

Botnets are the end result of many malware exploits—as viruses, worms, Trojans, drive-by or click-through attacks may deliver and propagate the bot payload. They are also a crystal clear example of how the objective of attacks have changed from hit-and-run high-profile grabs for fame to instead focus on stealth and establishing and retaining control of assets. Botnets are an ideal tool for the nefarious—they can command huge numbers of widely distributed systems at trivial costs. While it is hard to estimate how many systems are part of a botnet, the potential is staggering. For example, the much-publicized Conficker worm is estimated* to have placed more than 4 million unique IP addresses under the control of “bot-masters”. And this huge resource base allows the bot-masters to rent control of these resources to spammers or other agents looking for ways to generate attacks or other nuisances with low risk of being detected. In essence, they are allowing criminals and spammers to outsource the generation of their malicious activities. It is a frightening business model indeed.

It is also a difficult challenge for IT. Thanks to botnets, it is possible for an IT manager or CIO to get a call from out of the blue asking why their systems are attacking some other company or government entity’s systems. Or discover a botnets of 100’s of computers with their company. These type of events can happen to the best IT departments (even Intel or the US Government). Clearly, IT needs tools to help prevent such scenarios, and the antivirus and intrusion detection/prevention industry is working hard to keep up with the rapid growth in the delivery vehicles for bot code. The other weapon for IT managers is traffic analysis – looking for strange patterns of activity (such as bursts of e-mail traffic from selected systems or floods of network traffic generated against specific targets) that falls outside of business norms to determine if there is another business being conducted with their assets. While being part of a networked world has wonderful, powerful benefits, it is not without enhanced risk. A botnet is not a network you ever want a member of.

Intel technologies like Trusted Execution Technology (TXT) and instruction set optimizations such as STTNI can be part of these solutions. Intel® TXT can be used in solutions that help protect systems from software attacks which provide the malware payloads to compromise systems. In fact, Intel TXT (to be available with Westmere server systems) provides an entirely new protection capability for most systems—providing evaluation of the launch environment and enforcing “known good” code execution. This is important because most malware tools execute only once the system is booted—so Intel TXT provides a valuable complementary protection. And to help with the growing burden of run-time malware and attack analysis, new (with Nehalem) instructions that accelerate string manipulation can boost content inspection software ability to detect anomalies. And research and development will ensure Intel continues to develop and deploy building blocks to help IT address today’s challenges and tomorrow’s.

We can do that most effectively only if we’re trying to solve the right problems. Are your systems under attack? (yes, they are). What types of solutions are most effective for you? Where is the greatest exposure? Is the pain in stopping attacks or cleaning up after them? This is certainly worth thinking about—before some Government agency comes calling asking why your systems are sending them so much spam!

*http://www.confickerworkinggroup.org/wiki/pmwiki.php/ANY/InfectionTracking

Why upgrade your hardware when migrating to SAP ERP 6.0?

ennis.p.skillern@intel.com — Mon, 26 Oct 2009 19:10:06 GMT

Why upgrade your hardware when migrating to SAP ERP 6.0? Because it makes simple, practical, business sense that is all. SAP has identified several key reasons why customers are concerned about migration and several among them are as follows:

· Cost, Cost, Cost

o HW infrastructure cost is highlighted as one of the key barriers of migration

· Business Justification

o Is there a compelling business reason to upgrade the hardware?

· Additional risk of business disruption

o Migration of ERP environment is complex enough…how much more risk is there when upgrading your hardware?

From a cost perspective, the perception that hardware is a barrier to migration can be easily overcome. Based on research, the hardware cost as a percentage of the overall migration cost is only about 7%. That means 93% of the cost is in licensing, consulting, etc, etc. HW costs are only the “tip of the iceberg” and the real $ investment lies elsewhere in the equation.

Is there a compelling business reason to upgrade your hardware? Well…frankly, it does not make sense not to do it. One, we showed above that the hardware investment is minimal compared to SW licensing, consulting, service, etc. Two, the hardware requirements of ERP 6.0 are significantly higher than previous versions. ERP 6.0 requires up to 2.5x more CPU performance, 2.5x more memory and 1.5x more I/O! You will need the increased performance and scalability that Intel provides in our microprocessors. While the ERP performance requirements have increased 2.5x, Intel performance with SAP has increased 10X! Oh, btw…energy efficiency does matter and in your new ERP environment you will be able to consolidate servers and save on power and cooling costs. TCO will be significantly reduced and from hardware investment standpoint, you are likely going to recover the cost of the servers in a very reasonable timeframe.

From my discussions with the IT community, their major concern and number one focus area is to prevent business disruption and downtime. This costs companies real and significant money. The fact is that an ERP migration is a complex enough project managing the strategic, functional and technical portions. Adding a server infrastructure change increases fundamental risk. But, the key here is that it is done often and done successfully. Intel IT has published several whitepapers on the subject and communicated “Best Known Methods” to minimize that risk. A quick summary is inserted here:

Challenge:

• Convert Intel’s Worldwide Warehouse Management Software

• Upgrade from SAP* ERP version 4.7 to 6.0, change the DBMS, and perform a Unicode* conversion as well as a hardware upgrade

• Minimize downtime

Benefit to Intel IT:

• SAP ERP 6.0 improves Intel supportability

• Increases ease of integration to SAP NetWeaver* 7.1 Suite

• Provides access to Enhancement Packs and Enterprise Services

• Intel^® Itanium^®-based servers provide access to 128 GB of memory for database and SAP operations and significantly increased performance from true 64-bit processing

Key Results:

• Reduced downtime of upgrade by 50% by using Intel Architecture

In summary, upgrading your server infrastructure when migrating your ERP environment is a very, very complex task, but form a business perspective, it should be fairly easy to see the true benefits from combining the ERP migration and hardware upgrade at the same time.

Companies Benefiting from Server Refresh

hugh.mercer@intel.com — Mon, 26 Oct 2009 16:57:37 GMT

Every day, Intel® technology and platforms help companies solve business problems and challenges. Here are a few of the growing number of stories and reasons for choosing Intel processors and technology.

Winning: Humana – Healthcare product and services company

Humana continues to refresh its infrastructure with more powerful, energy-efficient technologies. For Humana, technology is vital for providing information and a full array of health benefit services to members. To replace an outdated facility, the company worked with Intel to design a state-of-the-art data center with a compact, energy-efficient infrastructure that could deliver flexibility and scalability.

Read about it here

The results:

· The Intel processor–based virtualized environment helps IT deploy new services quickly and ensure high availability.

· Humana added 25 percent more servers in 56 percent of the previous space while decreasing data center power consumption by 16 percent.

Winning: Emerson Electronics

Emerson reshapes its IT infrastructure for future growth, consolidating approximately 135 data centers down to four using Intel® technology–based servers

Read about it here

The results:

· 3,600 physical servers are eliminated by virtualizing on Intel processor–based blade servers, for 18:1 consolidation worldwide

· Power-saving processors help make Emerson’s new global production data center in St. Louis 31 percent more energy efficient than traditional data centers

Winning: Türkiye Finans Katılım Bank

Leading Turkish Financial Institution Drives Better Growth and Services with Intel®Technology. Türkiye Finans Katılım Bank makes use of the online Intel Xeon processor-based Server Refresh Savings Estimator

Read about it here.

The results:

Intel® Xeon® processor-based Server Refresh Savings Estimator¹ sets expectations clearly, predicting 80 per cent reduction in power/cooling requirements, and a 30 per cent increase in system performance already realized. With only 20 per cent of capacity currently utilised, bank has significant headroom for business expansion

Winning: Oracle IT

Oracle uses Intel® Xeon® processor 5500 series–based systems with Intel® Intelligent Power Node Manager to increase rack density and propel business growth. Refreshing its existing dual socket, quad-core servers on a three- to five-year schedule to increase processing capability and energy efficiency, but had no significant power management in use in the data centers.

Read about it here

The results:

More processing capability can fit within the data center power envelope because Oracle can actively manage power consumption for individual servers and applications.

· Energy savings of 35 percent are projected with Intel Intelligent Power Node Manager, for reduced operating expenses

· 50 percent more servers per rack saves data center space and enables more growth while keeping costs low

Winning: DataPipe®

DataPipe® retains a competitive edge by designing a new facility and refreshing existing data centers with cutting-edge technology that can deliver outstanding processing performance for a broad range of customer applications. Low-voltage Intel® Xeon® processors help DataPipe create a dense, energy-efficient infrastructure for managed IT services.

Read about it here

The results:

New Intel Xeon Processors Provide a Foundation for Cloud Computing. With the Intel Xeon processor 5500 series, DataPipe is creating

a robust virtualized server environment, Stratosphere™, for hosting customer applications.

Better together: engineering collaboration at the heart of breakthrough capability

andrew.i.fields@intel.com — Fri, 23 Oct 2009 22:00:37 GMT

As I’m new to The Server Room, I offer this brief introduction: I am a marketing manager in Intel’s Software and Services Group – looking after Intel’s collaborative marketing efforts with virtualization solution providers.

A couple weeks ago, Ken Lloyd blogged about the incredible changes in compute capability and performance brought by the Nehalem microarchitecture – and gave credit to the advances in software, too. I’d like to take the conversation a step further: did you know that the launch of VMware™ vSphere 4.0 in April 2009 represented a milestone of collaborative development? The combination of VMware vSphere and Intel Xeon processor 5500 based systems delivers astonishing performance in part because it is the result of a full cycle of collaboration.

Intel has a well established rhythm of technology innovation – and a lot of really smart architects who know a thing or two about cpu design – but we get innovative ideas from the outside, too. Over the years of the VMware alliance, Intel has received (and acted on) many requests for small changes in cpu circuitry…changes that would make virtualizing the cpu easier, more efficient, or add capability. A whole raft of hardware optimizations for virtualization were included in the Nehalem architecture. As Intel started to deliver early silicon for Xeon 5500 based platforms, Intel software engineers worked closely with VMware engineers – optimizing vSphere code to take advantage of the new hardware features to improve performance, increase efficiency, and add new functionality. The results? Check out this video from the launch of VMware™ vSphere 4.0 to see for yourself what “better together” really means. And the cycle continues – what can you imagine in the next round of collaborative innovation??

What is a digital workbench?

wesley.e.shimanek@intel.com — Fri, 23 Oct 2009 14:07:25 GMT

The digital workbench is like the workbench at home where you have pliers, nails and hammers that we use to build or fix things—the workbench holds all the best, most useful tools to complete a project and makes them available at your fingertips.

The digital workbench replaces analog tools with digital tools and software suites from ISVs (e.g. Altair, ANSYS, Autodesk, Dassault CATIA, Dassault SIMULIA, ESI, MSC, PTC, Siemens PLM and others). These ISV’s are all laser focused on enabling designers to move analysis further up the design chain. Couple this with recent performance gains available on workstations based on the Intel® Xeon® processor 5500 series from suppliers like Boxx, Dell, HP and Lenovo and you have the opportunity to now view your workstations as a digital workbench. The result is a new environment that enables users to rapidly test and refine their ideas potentially at the speed of thought.

The digital workbench, powered by two intelligent Intel® Xeon® 5500 processors based on the Nehalem microarchitecture, can help you transform complex and visually intensive data into actionable information at near-supercomputer speeds.

The Changing Face of the Digital Workstation

wesley.e.shimanek@intel.com — Fri, 23 Oct 2009 13:52:04 GMT

“Imagination is everything. It is the preview of life's coming attractions.” Albert Einstein

Today’s workstation can provide you with a magnificent digital canvas to create tomorrow today.

With workstations powered by two Intel® Xeon® 5500 series processors, engineers have the opportunity to create, shape, test and modify products before they become real. Engineers can now design, visualize and simulate products from the conceptual design phase through the entire manufacturing process. This is done virtually before any investments are made in a prototype.

“Experiment fearlessly.” “Innovation is bloody random.” Tom Peters

Peters, a world renowned author and management consultant, recognized that innovation is more art than science.

Consider this example: Taking innovation to an entirely new level, Boeing, in the late 1990s, employed a process known as algorithmic design to see what designs might be viable to meet a specified hypersonic aircraft design criteria. The algorithmic design process enabled computers to create and test new ideas against the specified design criteria without human intervention. As a result, more models were evaluated in less time, and a vehicle that was counterintuitive to what many engineers may have thought possible was evaluated. Innovation just accelerated.

Intel technology has seen dramatic changes since Boeing first tested the idea of algorithmic design in the last decade. Workstation performance has gone up Dual-processor workstations have yielded to workstations with two processors, eight cores and 16 computational threads. Science or simulation that was never tractable on a workstation before is now standard, and it is getting faster.

“I confess that in 1901 I said to my brother Orville that man would not fly for fifty years.” Wilbur Wright

You think all you need is an entry-level workstation with a single Intel® Xeon® processor. After all , you only do CAD—right?

However, as you begin to adopt modern workflows and realize the dramatic impact that simulation-based engineering or digital prototyping can have on your product development cost and schedules, you realize that the cost of the second processor and additional memory necessary to support digital prototyping was far less expensive than the cost of multiple physical prototypes and the associated time to produce them. Instead of investigating hundreds of digital prototypes, you only have time to look at a single physical prototype and ask: What if I …?

Those “what ifs” could have been played out on a dual-processor Intel Xeon processor 5500 series-based digital workbench faster, and your time and cost of physical prototypes could have been significantly reduced.

The digital workbench, powered by two Intel® Xeon® 5500 series processors, can have an enormous impact on your organization’s ability to design, visualize and simulate products, from the conceptual design phase through the entire manufacturing process, and it is all done virtually before a prototype is ever invested in. These digital workbenches exceed the computational power of the Cray C90 series, which in the 1990s was revered as the fastest ever.

Without question we all recognize that simulation and modeling have become indispensable tools in design. But visualization remains the principal conduit to transforming data into knowledge and actionable information. The digital workbench can provide you with both the compute capacity and the visualization capability you need to innovate faster.

If all you are doing is CAD on your workstation, then an entry workstation may be best your solution. However, as others around you adopt modern workflows that incorporate simulation-based engineering and digital prototyping, you may want to step up to a more comprehensive digital workbench solution that provides an entire suite of tools to help you play more “what ifs” locally and faster than ever before.

One more point on this: If you are stuck on the entry workstation, then you may want to consider a mobile workstation. While the immediate cost will be higher than an entry-level workstation, the real cost may be lower. With mobile workstations you can design with your customers and not just for your customers. You may be able to reduce the number of design reviews by innovating with your customer right there as spontaneous ideas happen. The real cost of a tethered entry-level workstation may be indeed be much higher than you think.

Join the revolution and innovate faster with the digital workbench powered by two Intel(r) Xeon(r) 5500 processors

Performance Impact of Intel® Intelligent Power Node Manager

enrique.g.castro-leon@intel.com — Fri, 23 Oct 2009 00:54:19 GMT

One of the first questions in my mind when I was first exposed to Intel(r) Intelligent Power Manager (Node Manager) was "what is the performance impact of applying Node Manager technology?" I will share some thoughts. The underlying dynamics are complex and not always observable and hence it's difficult to provide a definitive answer. Robert A. Heinlein popularized the term TANSTAAFL ("There ain't no such thing as a free lunch") in his 1966 novel “The Moon is a Hard Mistress”. So, does TANSTAAFL apply here? Node Manager brings benefits with the ability for the application to designate a target power consumption, a capability otherwise known as power capping. On the cost side, Node Manager takes some work to deploy, and has performance impact that varies from very little to moderate. On the other hand, Node Manager can be turned off, in which case there is no overhead.

Node Manager is useful even when it is not actively power capping but is used as a guardrail, ensuring that power consumption will not exceed a threshold. The predictable power consumption has value because it provides data center operators a ceiling in power consumption. Having this predictable ceiling helps optimize the data center infrastructure and reduce stranded power. Stranded power refers to a power allocation that needs to be there even if it's only for occasional use.

The performance impact can vary from zero when Node Manager is used as a guardrail to a percentage equal to the number of CPU cycles lost due to power capping when Node Manager is applied at 100% utilization. When applied during normal operating conditions, the loss of performance is smaller than the number of cycles lost to power capping implies because the OS usually compensates for the slowdown. If the end user is willing to re-prioritize application processes, under some circumstances it is possible to bring performance back to the uncapped level or even beyond.

Power capping is attained through voltage and frequency scaling. Power consumed by a CPU is proportional to frequency and to the square of the voltage applied to the CPU. This is done in discrete steps (“P-states” as defined by the ACPI standard.

The highest performing P-states are also the most energetic. Starting from a fully loaded CPU and the highest P state, the DBS assigns lower energy P-states as workload is reduced utilizing the Intel(r) SpeedStep technology. An additional dip takes place as idle is reached as unused logical units in the CPU are switched off automatically.

Node Manager allows manipulating the P-states under program control instead of autonomously as under SpeedStep. Since the CPU is running slower, this has the effect of potentially removing some of the cycles that otherwise could be used by applications, but reality is more nuanced.

At high workloads, most CPU cycles are dedicated to running the application. Hence, if power capping is applied, a reduction in CPU speed will yield and almost one-to-one reduction in application performance.

At the other end of the curve, if the CPU is idling and power consumption is already at the floor level. An application of Node Manager will not yield any additional power consumption reduction.

The more interesting cases take place in the mid-range band of utilization, when the utilization rate is between 10 and 60 percent, depending on the application (40 to 80 percent in the BMW case studybelow.) Taking utilization beyond the upper limit is not desirable because the system would have difficulty in taking up load spikes and hence response times may deteriorate to unacceptable levels.

We have run a number of applications in the lab and observed their performance behavior under Node Manager. Surprisingly, the performance loss is less than frequency scaling would indicate. One possible explanation is that when utilization is in the mid-range, there are idle cycles available. The OS compensates to some extent for the slower cycles by increasing the time slices to the applications, using up otherwise idle cycles, to the point that the apparent performance of the application is little changed. The application may need to be throttled up to re-gain the pre-capping throughput.

One way to verify this behavior is to observe that CPU utilization has indeed gone up in a power capped regime. BMW conducted a proof of concept with Intel precisely to explore the boundaries of the extent to which that application could be re-prioritized under power capping to restore the original, uncapped throughput. TANSTAAFL still applies here. The application is still yielding the same performance under power capping. However, since there are fewer cycles available due to frequency scaling, there will be less headroom should the workload pick up suddenly. In this case the remedy is simply to remove the cap. The management software needs to be aware of these circumstances and initiate the appropriate action.

The experiments in this proof of concept involved an application mix used at a BMW site. In the first series of experiments we plotted power consumption against CPU utilization by throttling the workload up and down, shown in red.

In the second series, shown in green, for each dot in the original curve we apply an initial power cap. This yields a performance reduction. The workload is throttled up until the uncapped performance is restored. This process is repeated with increasingly aggressive power policy caps until the original performance cannot be reached. The new system power consumption without impacting system performance is shown plotted in green. The difference between the red and green curves represents the range of capping applicable while maintaining the original throughput level. The execution and running at the green level yields the same uncapped system performance. However, since idle cycles have been removed, there is no margin left to pick up extra workload. Should it happen, performance indicators will deteriorate very quickly.

Under the circumstances described above, the system was able to deliver the same throughput at a lower power level. There was no compromise in performance. The tradeoff is in the form of diminished headroom in case the workload picks up. The system operator or management software have the option to remove this cap immediately should this headroom be needed.

And the winner of the Intel Xeon Workstation Sweepstakes is...

greg.wagnon@intel.com — Tue, 20 Oct 2009 21:38:33 GMT

Congratulations to Ron as the winner of the Intel Xeon Workstation Sweepstakes. He has been a member of The Server Room for over a year and was able to complete the quiz on the first attempt.

Good job!

"I was excited to hear that I won the Intel Xeon workstation sweepstakes. With its incredible performance, the system offers me the flexibility to use it in so many ways that I'm not sure how to best utilize it at the moment. It's a welcome problem to have and I look forward exploring the possibilities. Thanks to Intel and the Server Room team for providing a great resource to everyone!"

Thank you all for entering and look for more sweepstakes offerings in the near future.

- Your 'The Server Room' Admin's

I want my HPC….under my desk

jimmy.leon@intel.com — Mon, 19 Oct 2009 20:55:11 GMT

Are your “stuck at the desktop?” A May 2008 study from the Council on Competitiveness and IDC identifies the barriers large and small firms face in moving from desktop computers to High Performance Computing (HPC) servers.

Among the study findings¹, most firms:

- Reveal that they have important problems they cannot solve on their desktop systems

- Face three major barriers to adoption: lack of application software, lack of sufficient talent, and cost constraints

As a scientist, an engineer, or an analyst: Have you outgrown your desktop? What kind of new innovation or capabilities would the use of a HPC cluster give you? Imagine the capability to analyze data and gain more insight faster, or the ability to virtually prototype your ideas product more efficiently and cost effectively, or perhaps analyze, model, or simulate larger problems.

Few OEM products aimed at the personal or “desk-side” segment are making easier for end users to adopt HPC and help to overcome some of the barriers to adoption: the Cray* CX1*, SGI* Octane* III, and HP’s CP Workgroup System. These products are aimed at addressing the needs of the entry level HPC market and the workstation users that have outgrown their desktops. Both the Cray CX1 and SGI Octane III systems are Intel® Cluster Ready (ICR) program certified which means that Intel has worked with the hardware, system, and application vendors to ensure your configuration has been pre-tested for interoperability, so you can deploy with confidence. ICR helps to reduce TCO by making sure the components keep working together over the cluster’s lifetime, to increase availability and save time for IT departments.

So if your IT department cannot buy you full blown super computer, ask them for a personal super computer.

¹ Source: Reveal. Council on Competitiveness and USC-ISI Broad Study of Desktop Technical Computing End Users and HPC, May 2008 (http://www.compete.org/publications/detail/420/reveal/)

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

Somebody Blew The Whistle on The ‘Nehalem’ Effect

bryce.olson@intel.com — Mon, 19 Oct 2009 20:24:19 GMT

There’s a video going around from one of Intel’s top external customers. Before you see this (video linked below) I wanted to position this correctly. I caught up with Mr. X at an undisclosed coffee shop and got his approval to share publicly the messages that we would have rather had him go out with. Those messages are as follows:

Mr. X’s 4 year old servers were a burden on his organization, he spent all of his budget on just maintenance, nothing left for innovation.

He looked at his old infrastructure and determined that replacing them with more powerful-energy efficient servers from Intel was a strategic investment.

The New intel Xeon 5500 based servers provided the opportunity for him to innovate again. He claimed that these new Intel Xeon Processor 5500 (Nehalem-EP) are the best enabler of IT business value that he's seen in years.

They boosted energy efficiency, saved him big $ and extended his facility lifespan – now he doesn’t have to go build a new data center.

He replaced his old servers in a 9:1 ratio (getting rid of 9 old and replacing with 1 new) that enabled him to cut operational expenditures by 90% …And that savings alone is paying for the investment in these new servers in just 8 months.

By strategically investing in IT when his competitors hunkered down and cut spending – he is now positioned to grow faster and gain share as the economic upturn arrives.

Ok, now that I’ve had a chance to convey his real messages, you can check out this video.

How does a Real Server improve your life?

keith.e.lauritzen@intel.com — Mon, 19 Oct 2009 16:22:18 GMT

I’d like to introduce myself as a product line manager at Intel who has spent almost a decade ensuring we are creating the best servers to solve small business challenges. Part of my role is to influence future generation products and I’d like to learn more about your challenges, needs and desires so I can ensure we address them in our next generation products.

Here is a story I have heard in the past: “Ah geez, What Now? A customer just called to tell me they tried to enter an online order for my product and my web site is nowhere to be found. I am lucky they called, but so much for spending a Saturday at my kid’s baseball tournament! Now I need to drive an hour to my downtown office to restart and possibly fumble with my server. You would think that the desktop system that I am using as a server would just work so I can spend my free time with my family and my work time growing my business.”

I can’t count the number of times I have heard a similar story from customers and colleagues that are trying to grow a small business, manage their own computers and have a personal life. The answer to their problem is simple, buy a real server based on Intel®Xeon® Processors that is designed to keep your business running 24/7. Our latest Xeon processors and chipsets are not only validated to run 24/7, but include features such as support for error correcting code memory and RAID for server operating systems that ensure dependability and differentiate a real server from desktop system used as a server. However, a small business should not care about all this technical jargon. I believe they only care that their server runs 24/7 without failure, enabling them to focus on business growth and life.

What are your small business challenges? I’m all ears.

Keith