Every now and then a colleague, customer or acquaintance sends me a link to an article or blog that usually either features our products or those from one of our competitors. More often than not I get a lot of repeat sources (The Register, The Inquirer, CNET, etc…). The blog that comes my way most often is one from George Ou at ZDNet. One of his most recent blogs (A comparison of quad-core server CPUs) shows a bunch of our latest quad core CPUs and how they stack up against our previous versions as well as those from AMD. I won’t rehash the article here aside from saying it was positive for Intel and to say AMD’s issues with their quad core processors have been well documented.

Is Intel winning now because our products are superior? Are we winning because our competitor is struggling? Do these benchmarks mentioned in George’s blog tell the whole picture? As you can imagine we constantly ask ourselves these questions and many more internally. Our conclusions are that for processors and server platforms, as long as we provide leadership along several key vectors then our market share and overall market position will improve.

Manufacturing process, processor architecture, system architecture, cache size. These are four critical vectors that we have direct control over when we are making design and enabling decisions. At times in our past and in the present we have had leadership on all four. In those times we have won hands down. There have also been times where a competitor has chosen to focus on one or two vectors and that has led to their products being better for a specific area. The four vectors above are things that Intel focuses on but we always have to keep an eye on what end user value they deliver.

Our customers tell us they care about three main things; Price, Performance and Power. The three P’s. George’s blog shows that for one of the P’s (Performance) Intel has leadership, particularly on integer and floating point. There are similar looking examples for database, virtualization and pretty much any performance benchmark we have looked at recently. Thankfully for Intel, Performance is the “P” with the strongest correlation to success in the server market from a MSS perspective. We are also doing some amazing things with regard to Power. Some have been launched already and some will be coming soon with new products in 2008. The market is segmenting and we now make CPUs, chipsets and networking components that help OEMs build platforms targeted at high performance computing, mainstream enterprise, blades, workstations and emerging markets. Each has unique requirements with respect to the three P’s and one size no longer fits all.

I believe that overall George’s blog highlights the success that we are having today. I also think that there will be a steady stream of innovations that will be delivered in 2008 and beyond that will cause us to rethink how we deliver performance at the most efficient power level for the best possible price point. Virtualization, utility computing and charge back models for datacenter environments are all stepping up to take center stage. We all must innovate or become irrelevant…technological evolution waits for no one.

Shannon

With the old year grinding to a close and opportunities of a new year opening before us, it is a good time to take a moment and make some new year's information security resolutions. Some are good holdovers from last year and a few are new to the list. I think all are good practices to promote security and hopefully will keep a smile on my face throughout the year (no matter what cyber meltdown may occur).

1. Vigilance. Maintaining effective legacy security programs is critical. Loss of such capabilities opens the door to old, known, and well refined attacks
2. Embrace/Beware of disruptive technology. Double edged bleeding technology can be a blessing and a curse. It can reduce costs, increase efficiency, open markets, and change your way of thinking, but is also like walking into a darkened room in a horror movie. You never know what may jump out at you and in hindsight you may think "well that was painful". On the hot-list:
   • Virtualization technology in all its glory
   • Smart-phones and other PC OS/application based portable devices
   • Social media sites, tools, and accompanying behaviors
3. Careful with my PII. Our Personally Identifiable Information (PII) is more important than anyone can measure. I will handle mine with care, insure others do the same, and simply say ‘no' more often than not, when asked.
4. Don't be a fish. Just say no to phishing and spam. Filters are wonderful but a few will creep through. If it looks suspicious, it probably is. Don't be shy, even with the weird stuff sent by people you trust. Just pick up the phone and call them: "Hey Ralph, did you send me this executable attachment via email?" Is it not that tough.
5. Give an effort for disaster preparedness. Regular backups and encryption are my friends. Nothing huge mind you, but at least apply where it makes sense
6. Choose not to be a victim and let common sense prevail. Two types of victims exist: those with something of value, and those who are easy targets. Therefore, don't be an easy target and protect your valuables
7. Talk and share security. We are stronger as a team striving for security, than alone. The bad guys are working together; it is about time we do the same. Talk about security and share what works or doesn't. Don't be shy.

Not rocket science, but most of the great ideas rarely are. Feel free to chime in and be heard. What are your security resolutions for 2008?

vPro in Action: First Production Deployment of Intel® vPro in China

Jackson He

A technology is only as good as the value it delivers to the business. Intel® vPro is no exception. We can talk about the technical merits and tricks of how to deploy it wisely all day long - they are all very important. But in the end of the day, it is how the end users view the technology and value it in their day-to-day business operations. To this end, we have conducted quite many end user pilots. One of the successful stories was to deployment of Intel® vPro at China Ministry of Railways (MOR) Jinan Bureau. It was the first production deployment of Intel® vPro in China.

Before we dive into the story, here is some basic fact of MOR and Jinan Railway Bureau:

• MOR is the 2nd largest ministry in China with nearly 2 million employees. It is responsible for construction, maintenance, and operation of 80,000 km railway throughout China (~120,000 km by 2015).
• Jinan Railway Bureau, which oversees a major transport artery in eastern China that connects four of the country's most important export hubs, has seen its services improve by leaps and bounds recently.

Well, so what? What are the business problems that Jinan Railway Bureau has that warrant a solution based Intel® vPro Technology? Here is the problem statement the customer told us:

• With China's railway moving into high-speed railway operations (200KM/Hr in 2007 and 300KM/Hr by 2010), Jinan Railway Bureau requires near real-time data collected from railway lines to facilitate overall system management and train security/safety administration.
• However, frontline rail workers possess very few or no PC skills, a bottleneck that can potentially cause delays in the Bureau's railway management.
• Additionally, casual PC mistakes on railway lines can cause issues that require the onsite repair of IT support staff, who could hundreds of kilometers away at the Jinan Bureau Headquarter, a time-consuming and labor-intensive process that impacts critical PC usage.
• To lower the TCO (total cost of ownership), MOR started IT infrastructure consolidation and centralized IT staff at major hubs. Jinan is one of the major hubs. It will heavily rely on remote management technology to operate. However, when a PC is dead, there is not much they can do remotely.

This is a perfect case for Intel® vPro Technology and Intel® Active Management Technology. A solution based on Intel® vPro Technology was piloted in mid 2006 and 150 vPro systems went into production in 2007 the same day when China MOR operation speeded-up to 200KM/Hr operation - a key milestone in China railway history. Here is what covered in the solution:

• In planning the new Permanent Way Management Information System (PWMIS) deployment for Jinan Railway Bureau, the IT department of China MOR looked into adding manageability features at the PC hardware level to tackle manpower issues.
• Hardware-based PC management capabilities provide Jinan Railway Bureau with the ability to better monitor and recover their PCs in daily operations, bypassing the hassle of on-site PC operations and regular maintenance.
• In addition, Jinan Railway Bureau enjoys added flexibility in embedding hardware-based management features directly into their specially developed railway management software applications.

Customers are really happy with this solution. They were on stage with Intel for vPro product launch and share their successful experience - "In choosing Intel® vPro Technology, we not only considered performance issues, but also investment protection issues. Intel vPro Technology is a forward-looking architecture that will serve Jinan Railway Bureau well into the next decade." stated by Mr. Liu Teng, IT Director of Jinan Railway Bureau.

What next? China MOR is very interested in Intel® vPro success in Jinan. Several other railway bureaus are following - Shanghai, Lanzhou, and Beijing are following the example and apply Intel® vPro Technology in different applications. We are working very closely with our China MOR customers to make vPro Technology a standard for their IT operations. Stay tuned for more exciting news of Intel® vPro.

I was recently attending a holiday dinner party when someone asked what I did for a living......after about 30 seconds of explaining that I worked for Intel on virtualization technologies and innovation in the data center, their eyes glazed over and they began to reach for a holiday refreshment.

Anyone else have a similar experience??

Perhaps, that would be my reaction if I sold mud flaps, distributed lettuce or traded stocks and bonds all day. As I began to retreat into my blackberry (geek speak for I was completely bored), my friend's wife asked me a question: "What the difference between MySpace, Facebook, Yahoo and Google? I don't really understand it but my teenage daughter and all of her friends spends hours every week on these sites." Eureka! 2 Guys and a dog had saved me from a night of sheer agony. More on my response to the question later.......

The question got me thinking back and reflecting a little on our collective journey the last decade in the data center, what has happened, what has not and the importance of innovation....

In the mid-90's when Oracle, Microsoft and Open Source established their market positions, Netscape was a media darling, and graduating from Stanford insured a $3-5 Million venture capital raise, innovation seemed to be everywhere. Juniper, Ciena, Marconi, Cerent, JDS Uniphase, Nexabit, Alta Vista, Transmeta, Brocade, McData and many others re-established an era of excessive ( a good thing in my opinion) innovation in the Data Center. Even Captain Wireless, Craig McCaw, got involved, realizing that without a proper infrastructure 1st mile Broadband (wired or wireless) consumer innovation is not possible. My point, the data center was then and is today, the foundation of internet innovation.

I would be remiss if I thought innovation had kept pace with what is possible. As technology professionals, we have become encumbered by lawyers, regulatory commissions and avarice, we have experienced our fair share of disappointments along the way. Y2K?, Sarbanes-Oxley, Netscape's eventual implosion, AOL, etc.....Fiber Channel, once considered a foundational element of the 21st century data center, has been slowed by avarice, arrogance and meaningful innovation due to lack of standards, ease of deployment and manufacturing materials technology innovation. Ethernet and MetCalfe's law have won the day, in my opinion, for the opposite reasons: standards, ease of use and manufacutring innovation. Virtualization has revisited mainframe usage models to establish a new era of innovation, which looks a lot like the late 60's and early 70's, only at a fraction of the cost. Storage innovation has allowed children of today to collectively hold more technology in the palm of their hands than the greatest scientists of their grandparents generation could have ever imagined or forecast. In the data center this has meant that between 2-3% of all power consumed in mature markets goes to support our computing needs of today.

To me, this suggests a paradigm shift for us all, a responsibility as technologists, scientists and yes even regulatory commissions to examine data center innovation in a new, thoughful and critical way as we embark on the new era. If 2 guys (or Gals hopefully soon) and a dog can change the dialectic of the human existence (at least in some mature markets) then we must take the responsibility to insure innovation occurs every year, even if the media and venture capitalists are not watching. We have been slow to innovate transport technologies, materials technology, software management tools, and energy efficency in the Data Center. We can do better.

In my opinion, by the end of the decade we need to take an optimistic goal of deploying 10Gb (at least) ethernet on every server in a data center, storage virtualization across unlimited distances with latency under 250 milliseconds, virtual machines migration to the best available compute resources, policy-based software management tools, biometric authentication for consumers/sellers, recycleable components and zero downtime in the data centers if we hope to maintain investments for the next generation of "risk" innovation.

Back to my dinner party response: "The difference to your daughter between Google (2 guys), MySpace ( 2 guys and surfboard), Yahoo (2 Guys) and Facebook is minimal. Each has found a way to connect with a particular network of subscirbers in a meaningful way. The difference in the data center, for a geek like me I explained, is meaningful. One company has made their data center, the center of innovation in design, deployment, use of renewable energy and delivery of content. One has made the content aggregration and user interface their innovation. One has made the social aspect of entertainment and innovative advertising their innovation. One has real-time interactivity and blogging as the cornerstone of their innovation, which requires fewer compute resources, less consumption of energy resources and potentially "liquid" scalability of the business model. Each is responsible to you to deliver a safe, interactive environment for your daughter and her friends to enjoy each other in a way that was not possible only a decade ago. For me it is a very exciting time to watch our world evolve and communicate with each other for the 1st time, in real time, on a global basis, without encumberance. I'm just glad to have been a small part of the evolution."

Her response: "Wow, I had no idea....I guess. Have you seen our new mud flaps?"

See the full report here: http://communities.intel.com/docs/DOC-1283

In a large enterprise like Intel, there are many different ways that software is provisioned for specific usage models. The general business user's client build contains common applications to support day-to-day tasks. On top of that build, other software applications are installed by the user using a repository of installation kits. The current self-service model works but it could be improved by taking a page from the Software as a Service (SaaS) approach.

With SaaS, services are delivered on-demand over the internet using a consolidated backend infrastructure. Typically, SaaS application usage is metered and billed on a per-use basis. If we take some of these concepts into the enterprise, we can explore benefits of boosting productivity and lowering costs. Productivity from the user standpoint is improved by automatically providing application updates and patches. Users no longer have to download new versions from the repository and take the time to install them. Lower costs could include a new strategy to manage licenses. For example, better tracking of application usage could lead to a plan to reclaim unused licenses. Information generated by application usage ensures that the correct licensing is purchased during supplier negotiations for renewals.

I have been working as a full-time performance engineer at Intel for 6 years. I started by benchmarking server products for performance validation and now I focus on the TPC-C and TPC-E OLTP server benchmarks. I have used a variety of workloads in this job and spent time optimizing each level of the performance hierarchy: application, system, and processor. I, like many of you, have learned the "tricks of the trade" the hard way: by trial, error, and success. I'm sharing now, so you can all benefit from the things I've picked up along the way.

Let's start with some general methodologies to follow when tuning performance, whether you do it full-time, as a hobby, or just in your spare cycles after getting your "regular work" done. I will follow up with a more detailed post on each habit individually.

1. Ask the right question: Why are you tuning your platform? What level of performance are you hoping to achieve? What do you (or your users) care most about: raw performance, cost/performance, performance/watt, or something else?

2. Start at the top: The first and easiest part of your application server to tune is the hardware itself. Move on to the software and workload only after you feel confident that you have removed any system-level bottlenecks.

3. Know your Platform: This should be where you begin your system (hardware) tuning. The first thing, which I can't stress enough, is to get a block diagram of your platform. Then study it!

4. Know your BIOS: Server BIOSes these days come with more and more options. Be sure to give your new platform's BIOS a once-over. Pay particular attention to options relating to performance and power.

5. Know your Workload: To quantify performance, you need a workload! Some examples: web server response time, boot time, frames rendered per second, simultaneous connections supported, etc. Understand as much as possible about how the work gets done.

6. Try one thing at a time: Little changes that seem harmless can significantly alter the behavior of your system. Or worse, they can interact with each other to wreak havoc. Always try one change at a time, and for goodness' sake, do habit number 7.

7. Document and Archive: When you change something, log it! For each experiment you do, store your hardware and software configuration, performance level, and any collected data.

8. Use the right tool for the job: There are free data collection tools out there for various levels of the tuning process. System tuning tools include such as Performance Monitor for Windows or Sar for Linux. Application-level tools include Intel ® VTune^TM for both Windows and Linux.

9. Don't break the law: Amdahl's Law, that is. Amdahl's Law tells us the maximum amount of performance improvement we will get from a particular enhancement. Amdahl can help you set your expectations properly and clue you in to when you should be suspicious.

10. Compare apples to apples: Todd Christ reminds us of this habit in the last paragraph of this post. Don't compare the performance of mis-matched systems. If you must do it, know exactly what the differences are: the processor, memory type/speed/vendor, a software component, chipset, etc. Dig into the configuration details!

So now you have the high-level list! Stay tuned to The Server Room for more information about each habit in the coming weeks.