About 3 months ago I delivered a 2-part viedo series on the benefits of 45nm process technology (part 1, part 2). As time has progressed, the intel roadmap has continued to evolve and deliver increased benefits. On Sept 8th 2008, we introduced four new 2-socket processors in our Xeon 5400 product line and this past Monday (Sept 15th), we introduced a whole new series of products for our 4-socket product line, the Xeon 7400 series (codename: Dunnington). All of these new products feature 45nm process technology and the enhanced Intel Core Microarchitecture.

Here are some highlights of the benefits available for IT solutions

 Better Performance: Xeon 7400 features up to 6-cores and 16MB cache per processor. It is staggering to think about what an individual server is now capable of doing.

o Over 1 million transactions per minute (8 socket TPC-C* result)
o Over 600,000 transactions per minute (4 socket TPC-C* result)
o Over 500,000 business operation per second (4 socket Java SPECjbb*2005 result)
o Learn more about performance results of the Xeon 7400 products here

 Energy Efficient: The performance of 45nm processors (including the 6core) is being delivered in the same power/thermal envelopes as previous quad-core processors making the performance per watt ratio particularly appealing and beneficial to managing data center space and minimizing cooling challenges while growing performance capability. Many customers are refreshing older servers and seeing dramatic reductions in total cost of operations and space requirements. Evaluate your potential benefits with the Xeon estimator

 Investment Protection – All 45nm intel xeon processors (xeon 7400 and xeon 5400) are platform compatible with their 65nm quad-core predecessors (xeon 7300 and xeon 5300 respectively) so adoption, certification and integration into existing IT environments requires less effort.

 Flexible Virtualization: All 45nm Intel Xeon processors contain a technology called Intel VT FlexMigration that allows newer 45nm processors to be live migration compatible with previous 65nm intel xeon processors. So with current virtualization software support, IT customers can migrate virtual machines across multiple generations of intel processors, all in one big pool of computing.

 Better Business and Science: Many of the world’s top companies are using Intel’s 45nm products coupled with their software solutions to enhance their IT infrastructure. Last week Cern opened the Large Hadron Collider focused on recreating the big bang . Read more about how 45nm intel technology is playing an integral role in gaining insights into the formation of the universe or check out how your peers are benefiting from new technology at www.intel.com/references

 Eco-Friendly: If your company or boss has a green thumb, you may be interested in knowing that the new Xeon 5400 products are now built with materials which are both lead and halogen free (halogen is a material known to contribute to global warming)

Finally, I came across this video where Nathan Brookwood (analyst from Insight 64) discusses the new Xeon 7400 product (Dunnington) and his outlook on technology roadmaps moving forward.

In the next few weeks, I will be compiling and answering the top 6 questions around 45nm … so ask away.

Chris

This is the 2nd in a 3 part series of video blogs that looks at Virtualization, Grids and Cloud computing. Follow this link for the first part: Part 1

The videos explore these concepts first individually and then try to show that taken together the combination is greater than the sum of individual deployments of the techologies. In reality, all three are required to begin to realize the vision of the dynamic, efficient datacenter but I would caution that these are necessary but not sufficient to realize this full vision ... well ... is a topic (set of topics?) for another day.

As you view the video please bear in mind that there are a couple of underlying assumptions in the statements I make in the video - unfortunately these got eliminated in the editing in trying to meet video duaration constraints. A quick recap of the assumptions:

a) the target environment is the enterprise (both enterprise IT and enterprise data centers) - some of the thoughts apply to SMBs but may not always.

b) the discussion on clouds is really focussing, primarily, on "Internet" clouds and not "Private" clouds (there is a reference to and a motivation for "Private clouds" when the technologies are brought together but in this discussion on clouds the focus is on Internet clouds unless mentioned otherwise).

c) The perspective on Grids in the video is broad - Most folks are used to associating Grids with HPC - it would be very helpful in this video to suspend this association (at least while watching the video and if I can get you to, maybe, into the future as well). This association with HPC is very limiting and represents a use of Grids and does not illuminate what Grids really are or, more importantly, their potential.

This and the previous video introduces the concepts as I see them. Some tangible examples in how they may come together is presented in the next video ... promise ...

So here is the video:

Now that you have heard and seen the video .... a few more observations not discussed in the video ...

• Grids represent an infrastructure management paradigm - actually once you step beyond the base machine virtualization (where the opportunities for real differentiation are fast dimnishing) you will find that solutions that most vendors have or are developing to manage these VMs borrow heavily and, in some cases, almost entirely from Grid technologies - but they won't tell you that. (Once you take the "broader view" it becomes apparent that many Intel platform technolgies become very relevant to Grids and so Intel platforms can be deployed as more than just the "simple and commodity" hardware that they are currently viewed and deployed as)

• Another point to note is that Clouds and Grids are closer than one may think. In many cases a cloud is realized by a simplification of a Grid that is made possible by application to a defined context determined by the cloud service offered. Furthermore some of the complexities of Grid computing (under the covers) have been masked by the introduction of a portal or some other simplifying assumptions and implementations. Many of the well known clouds are implemented using Grids. Nonetheless it is very important to keep Clouds and Grids distinct so that one can understand these paradigms and extract maximum value. The moniker cloud represents a use paradigm (against an highly elastic service) whereas Grids represent an infrastructure paradigm.

• On a larger note: One way to bring these topics together conceptually is to see virtualization as the paradigm to substantiate the entities (resources or otherwise) that can be/are visualized in a context, Grids as the paradigm to manage these virtualizations and Clouds as the paradigm for use of these managed virtualizations.

I will build on these assertions in my next video ... In the meanwhile am looking for discussion on these topics -

• What do Grids and Clouds mean to you?

• Do the views represented here make sense or are there other ways in which one may approach these topics?

• What are some interesting ways you have used these technologies in your line of work? What are some problems that were solved or new usages created?

• Are Grids as a topics of discussion dead/passe or are they as relevant today as they were a few years ago - why?

Back at IDF for Day 2 and still wrapping up some exciting news coming out yesterday. I met with Robert Zuber (IBM WW Marketing Manager)and Mike Moreno (Intel) and we talked about how IBM and the DB2 team, along with XEON 7400-series processors achieved this milestone of the Industry's First 1M+ TPC-C result. Here's a video with Robert and Mike in the Technology Showcase.

Check out the official Transaction Processing Council Site for details on the system configuration and full results.

Hank Lea and myself (Jason Davidson) will be covering the Eco-Technology debates at the Marriot Hotel in San Francisco on Monday, August 18th. We will also be hosting a blog talk radio show around this event at 5:15 PM.

In my tenure at Intel, I have had the pleasure of walking into major companies, educational institutes, non-profits, and government agencies to talk technology with many great people. “How green is this solution” is a topic on many minds lately – no matter which topic of discussion. Being an engineer by trade and scientist by education, I will typically dive into the details of around each component’s power consumption and the discussion ends with some simple math multiplying a number of units by their thermal numbers. However, there is so much more to the overall impact, and as I walk in and out of these locations, I am always amazed at the number of larger issues with much larger impacts that are unresolved or overlooked. For more information on these items, here is a blog.

The Eco-Technology Great Debates provide a unique and entertaining forum to expand your understanding of today’s most pressing data center and IT issues. Come hear industry leaders take up both sides of some of the hot topics facing

the industry.

Attendees will learn about the pros and cons of high-density computing versus low-density computing and ready-to-use container data centers versus traditional brick and mortar data centers. There will also be a panel discussion on energy efficiency metrics, which will take a look at everything from chips to cooling systems and how they play a role in energy efficiency.

The energy consumption of servers and data centers has doubled in the past five years and is expected to almost double again in the next five, costing about USD 7.4 billion annually.¹ There is no single right answer on what to do about this critical situation. Take an active step in solving this challenge by attending *The Eco-Technology Great Debates* and IDF at a special money-saving price. Register for IDF now and enter promo code *CLOECOT* (admission to the Eco-Technology Great Debate and a 2-day pass to IDF) or enter promo code *CLTECOT*(admission to the Eco-Technology Great Debate and a full conference pass to IDF). The debate takes place at the San Francisco Marriott Hotel (located across the street from IDF).

¹ [EPA Reports Significant Energy Efficiency Opportunities for U.S.

Servers and Data Centers (August 2007).|http://yosemite.epa.gov/opa/admpress.nsf/0de87f2b4bcbe56e852572a000651fde/4be8c9799fbceb028525732c0053e1d5!OpenDocument]

<!-- /Item 3 ><! /Eco-Technology -->

Using some data from our own IT group, we developed a simple ROI calculator. This tool provides an estimate of performance and IT cost savings of refreshing older servers with new ones. Below is a screen shot of the calculator that is now available on our new server tools section of the Server Room. Give it a try and let us know if these assessment tools are helpful?

Virtualization is without a doubt a very hot topic these days. Companies continue to look to server virtualization to increase the utilization rates of their systems and lower overall deployment and management costs. The basic model of a virtualized server is depicted below:

Essentially, you have a VMM (Virtual Machine Monitor) SW layer that talks between hardware and software and allows each virtual machine to successfully use what it thinks is one network port. This is a pretty straightforward model and it directly addresses the general reason for virtualization which is that generally the server may not be utilizing its processing power in full and is thus wasting CPU cycles.

There is an interesting result of this consolidation onto a single physical box with several Virtual Machines. In addition to consolidating CPU processes, you also effectively consolidate I/O bandwidth and switch processing capabilities onto the same platform. The overhead of this switching limits your bandwidth, adds CPU overhead, and effectively reduces the benefits of server virtualization. In some cases you may have a new problem in having created an I/O bottleneck.

This makes a lot of sense if you think about the fact that in essence, what you are doing is merging 5-10 machines that each had 1 or 2 ports of Gigabit Ethernet (all connected via a switch) into a single machine. This new server probably needs to have at least 6 ports or more of Gigabit Ethernet and may even require 10 Gigabit connections just to be able to support the new consolidated workload.

Enter Virtual Machine Device Queues (VMDq):

In order to help the I/O congestion associated with the additional VMM software switching in a virtualized environment, Intel implemented a technology called VMDq in our latest Ethernet NICs and silicon. VMDq is a technology specifically designed to offload some of the switching that was done in the VMM to networking hardware specifically designed for this function. This drastically reduces the overhead associated with I/O switching in the VMM which greatly improves throughput and overall system performance.

Below is a diagram that summarizes the new virtualized server stack with VMDq enabled:

On the receive path, VMDq provides a hardware ‘sorter' or classifier that essentially does the pre-work for the VMM of directing which end VM the packets should go to. The NIC or LAN silicon is performing a hardware assist for the VMM layer.

On the transmit side, the packets are serviced round robin style to avoid "head of line" blocking and alleviate potential quality of service (QoS) issues.

The immediate question I expect is "So, don't the VMM vendors have to support this?" And the answer is yes. Intel is supporting this feature today on shipping platforms, but you do need to work closely with the VMM vendor to make sure the whole stack works as designed.

Just this week Intel announced that our VMDq capability will be supported in VMware's upcoming ESX release. This is certainly a big step towards wide support of network virtualization performance enhancing features.

Ethernet technology has grown and become more important over the last 25 years, and the trend appears to be continuing on course.

Ben Hacker

--

For more details on VMDq, there is a VMDq Whitepaper, and an Intel® VT for Connectivity Datasheet located on our website.

In the second comment around the right time for datacenter refresh, I'd like to look at Costs. Power is covered in the comment from Chris and I covered some comments on Space already in the discussion forum. So what it really boils down to is cost of running your existing datacenter versus the costs of throwing the servers out and replacing them. It is clear also from the other comments, that it doesn't make sense to throw out servers which are utilized in average 15% and have them replaced by new servers, which are 5 times faster and utilize the servers 3%... Great achievement hu?... Server Refresh makes therefore most sense to do only when consolidating the environment. How do I consolidate the environment? By using virtualization. See Helmuts blog and the whole theme next week on that topic.

Therefore let's look at the real cost factors, when refreshing the servers:

• Cost of new hardware: That is obviously a significant capital expenditure and starting at about 2000$ for a reasonable DP server. But the trick is also that a lot of server companies offer financing models which make this an operational expenditure. But key is also to understand, that by consolidating your servers at the same time the depreciation costs of the servers may actually decrease, as you have less hardware to depreciate!

• Maintenance costs: Again, reducing the number of servers running given applications, and at the same time unifying the environment helps significantly to reduce the maintenance costs. This can be a significant step in unifying on a given OS or hardware platform.

• Power consumption: Similar to utilization, it doesn't make sense to just look at the power consumption by server, but at the consumption by performance and therefore I can save about 38% in power bills, on a given workload vs. the previous generation hardware and about a 10^th of the power of hardware which is 2-3years old. Again, obviously only, if I do this in combination of consolidating the servers. Trick often is, that those costs are often not taken into consideration, as those are not billed to the IT department but to the facilities group. So it becomes an executive decision to ensure they are looked at!.

• Switching costs. Obviously very hard to measure, as this depends on the environment of the customer. And I talked to the customer who said: "No I will never touch this AS400 system, as it just runs and runs and runs." On the other hand I had a customer who replaced just those AS400 systems and saw huge synergistic effects, because he put the application on a standard based architecture and was able to finally integrate it in the other production system and therefore have one reporting and analytics tool.

I try to make a long story short. This is not something you do very often, but you don't get married every year either. But most of the time it's worth going through the efforts. So thinking about replacing the servers which are older than 2-3years is definitely worth while and often an effort which pays off in the first year!

Welcome to The Server Room, we've put together some quick videos today for you in order to put a name to the face of some of the bloggers and get a more personal touch for our interaction. Arijit Bandyopadhyay, Nikhil Sharma and yours truly are found below... Enjoy! and BLOG AWAY!