The Server Room Blog

Dunnington Shines at IDF-New World Records Announced

whlea — Wed, 20 Aug 2008 04:16:19 GMT

Big news today at IDF SF08...Intel Exective VP, Pat Gelsinger delivered his keynote address here in San Francisco, Moscone Center. Innovation is always a big topic at IDF and today is no exception. Intel announced today new world record performance for the XEON 7400-series processor, code-named "Dunnington". And just what are these world records you ask? Watch the video for stunning results from Fujitsu Siemens (SPECint), SUN (SPECjbb, Dell (TPC-E), HP (4S TPC-C, SQL Server) and IBM with an Industry First 1.2 Million TPC-C result on Intel Architecture. Enjoy the video!

How Would You Like Your Benchmark?

C_Peters — Wed, 16 Jul 2008 06:25:22 GMT

Today, I met with Tim Denney (a summer intern here at Intel) who is working for our performance analysis team. Tim told me that he had built a tool allowing intel employees to compare performance of certain SPEC published benchmarks (www.spec.org) across a variety of processors.

Tim demonstrated this analysis tool that searches all the integer and floating point publications on www.spec.org across a range of architectures (Intel, AMD, UltraSPARC, Power). You can input different processors and then the tool returns the published results available and a simple graphical display of the best published results for the processors chosen.

After meeting with Tim, I thought about the numerous "Ask an Expert" questions I’ve received on OpenPort in the last 6-9 months where people have asked me where and how they can compare performance across a variety of processors (dual core to quad core, different speeds, 1S to 2S to 4S, etc).

In took me about a nano-second to realize that your input would be really helpful in developing an improved user interface. So here is your chance. I encourage you to try this performance comparison tool and respond back with your ideas on how we can improve the tool and user interface. I can’t guarantee that we can implement every suggestion, however, I do guarantee that we will listen.

So … How would you like your benchmark?

Got That Virtual Feeling?

C_Peters — Tue, 08 Jul 2008 16:54:00 GMT

Working in High Tech means that most of us don't ever slow down - if we do, we risk falling behind. As a result, I usually find myself more more stressed than relaxed (just ask my peers or my wife).

So when I find good humor, I like to share. I found this video snippet about virtualization at www.talesofitutopia.com and it put a smile on my face. It is a little scarry that i can relate to more than one of the characters (the boss, the IT guy and even to some extent the JINX). Which character do you relate to?

Virtilization anyone?

Server Performance Tuning Habit #5: Know Your Workload

Shannon Cepeda — Tue, 17 Jun 2008 15:46:14 GMT

Here's the 5th follow-up post in my 10 Habits of Great Server Performance Tuners series. This one focuses on the fifth habit: Know Your Workload.

Spend some time getting to know your workload.

The idea of a "workload" is integral to the concept of performance. The workload is the set of software and tests that you run on the server in order to measure its performance. Also part of the workload is the is concept of the "metric", which means, the number you will use to quantify performance. You should understand as much as you can about your workload in order to characterize and interpret your system's execution.

Let's look at the real-life example of a car's fuel economy. The EPA measures fuel economy using 2 workloads: city and highway. Each workload tests different aspects of the car's performance, and the metric used to quantify that performance is miles per gallon (MPG). Like the EPA's fuel economy test, a good workload for server performance tuning should have the following three characteristics:

Measurable - There is a quantifiable metric.
Reproducible - Measurements are repeatable and consistent.
Representative - The workload should be typical of normal operating conditions and should stress the parts of the system (including code) where performance is most critical.

Depending on the usage model for the server(s) you are tuning, some example appropriate workloads might be: loading websites , processing XML, encoding/decoding MP3s, responding to database queries, rendering frames, etc. Metrics could be time to run, number of users serviced, transactions processed per second, etc. If your metric is time, take special care that you are measuring it accurately.

After choosing or creating a suitable workload, spend some time getting to know it. Measure the variance between runs. Use O/S and processor-level tools (to be discussed in the blog for habit #8) to sample the workload's characteristics at various points during its execution.

One thing to remember about sampling is that you want to make your sample interval at least as long as the amount of time it takes to complete a unit of work in your workload. For example, suppose your workload is a stream of web page requests and you are measuring response time. If the longest response time you see is about 2 seconds, then you want to make sure you take samples over 2 seconds in length. It's best to use a multiple of your longest operation time, so 4 or 6 seconds in this case. This way you can be sure your samples include one complete operation in the workload. Then try to determine if the workload is stable - meaning, do the characteristics vary at different times during execution? (If so, you will need to sample more often to understand the workload or possibly split it into phases). Use the data to get an idea of your workload's CPU, memory, network, and I/O usage.

At the application level, become familiar with the software stack you will use. How is the workload generated (user, clients, test files, etc)? Understand the major operations that occur - what components of the O/S are needed? What device drivers are used? And finally, study the application(s). Know whether the application(s) being tested are single- or multi-threaded and as much as you can about the internals.

Choosing (or developing) an appropriate workload is necessary for correct performance measurement and tuning. Being as familiar as you can with the workload will help you to interpret your performance data and identify areas for optimization.

Keep watching The Server Room for information on the other 5 habits in the coming weeks.

Why 45nm ... What's Next (part 2)

C_Peters — Wed, 11 Jun 2008 21:40:20 GMT

Last week, the first part this video series focused on the energy efficiency benefits of 45nm. The 2nd part of this video (below) is focused on the benefits of 45nm for virtualization and the intel processor roadmap including what's next in 45nm processor technology - the Dunnington and Nehalem-EP products

Is this information useful to you? why or why not?

Chris

Quad-Core ROI Calculator

C_Peters — Mon, 09 Jun 2008 17:18:06 GMT

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?

Why 45nm ... What's Next

C_Peters — Wed, 04 Jun 2008 19:58:52 GMT

Following a recent interview I conducted with the Register on a related subject, I was asked to talk more about Intel's current 45nm technology and our roadmap for new technology later this year. Join me in a two part video series where I discuss 45nm and beyond.

Part 1 (below) discusses the technology and benefits that 45nm xeon processors deliver for IT today.

Tune in next week to hear Part 2 - what we have planned for future enhancements to today's xeon products - the Nehalem Processor and Intel QuickPath architecture.

Chris

Big Servers are Back!

bryceolson — Wed, 28 May 2008 20:05:23 GMT

One trend that is really starting to take shape in the server industry is that big servers are back! That doesn't mean big servers ever disappeared off the map. Historically bigger servers with 4 or more processor sockets have been 7-8% of the server market from a volume perspective. And bigger servers have always been used for scalable, data-demanding enterprise applications which IT values for it's performance, headroom and reliability. What we're seeing now is a greater shift in popularity towards these servers as IT invests more and more in this direction.

So, why is that? Well, check out this video and then let me know if you agree or disagree. After you watch it I'd also be curious to learn more about what you value as the most important buying criteria when you go big.

Servers: Burden or Benefit?

C_Peters — Wed, 21 May 2008 14:42:33 GMT

Join me for a discussion with industry leaders and IT professionals on this topic on the ArsTechnica webforum.

There is a lot of proof supporting both sides of this question. Maybe ... Just maybe ... new server technology can help turn today's IT burden's into tomorrow's business benefit?

Share your opinion or Tell us your experience.

Virtualization - Who Cares?

S_Poulin — Wed, 14 May 2008 00:26:17 GMT

I have visited a number of customers recently. The discussions are usually straight forward where I provide them with a download of our current products, I tell them about things that we are doing in the future and along the way I ask them some questions about trends that they are seeing with their businesses. It will come as no surprise that enterprises are trying to keep up with their current requirements while also squeezing out increasingly flat or dwindling budgets to do something new. Many are turning to virtualization as a way to do more.

So who cares? CFO's care. I went out to visit a leading Fortune 500 company based on the West Coast of the US. Keep in mind I am planning to discuss our server platforms, why I believe they are leadership on performance and power and also all of the great new virtualization features we have recently introduced or will intro in the future. Before we get started they proudly walk me through their new datacenter and I stop in front of a rack that has two servers in it. Two 2U two processor servers. It is right next to another rack that has four servers in it. I inquire as to why both racks are only partially full and I receive a response that says one is owned by Finance, one is owned by a business unit. IT just manages them. You can look at this two ways. The glass half empty way would be that they are wasting an incredible amount of datacenter space and they are hopeless. The glass half full way would be that this is a great opportunity to really deliver value to this company's bottom line by first convincing them that physical consolidation (full up their racks) is important, then showing them a path toward application consolidation and finally sharing a vision of datacenter virtualization that includes compute, storage and networking. Their CFO will care.

IT employees care. One theme that seems to be coming through loud and clear is that people who drive some form of virtualization are usually considered as innovators or leading edge thinkers within their company. I have heard the term "IT Hero" to refer to someone who has delivered on a high ROI project, usually these days through the use of virtualization. I have met a number of IT folks at conferences and during visits and it is uncanny how many are trying to dig for more product information and how eager they are to hear about what new features we're putting into CPUs, chipsets, networking devices. A quick search of Youtube found this case study (here) that sums up the sorts of things I have heard.

It is also increasingly important that all of this stuff works well with the software, VMM and OS vendors product offerings. I know we are working closely with all of the ecosystem players because if we come out with an amazing new feature in our components it would be wasted if the VMM, OS or software didn't take advantage of it. There is some interesting banter here (here) about some of the pros and cons with virtualization. We are busy working on features that improve the performance and simplify the experience end users have when they virtualize. Why do you care about virtualization? What are you doing today that you couldn't do a year or two ago that has been made possible because of virtualization related technology?

45nm and Beyond

C_Peters — Wed, 23 Apr 2008 15:45:18 GMT

Technology moves at such a rapid pace - it can often be mind-boggling. Even working directly with the product teams at Intel, I sometimes have difficulty keeping pace. The good news is that there is a tremendous opportunity today to be captured thanks to this rapid innovation, as well as a steady stream of advanced technology that IT can use to better support business and gain a competitive advantage. Recently I was interviewed by Tim Phillips from the Register about the current 45nm Quad-Core Intel Xeon products and the next generation Intel platforms based on the Nehalem processor.

A few years back, Intel fundamentally changed the way we design and develop our underlying micro-processor technology. We streamlined our innovation and accelerated it's pace. Internally, we call this new model Tick-Tock. I like to call it shrink and innovate.

A "Tick" is a manufacturing process shrink that delivers smaller silicon with higher speeds, more transistors and lower power consumption (example: moving from 65nm to 45nm process technology). The 45nm quad-core xeon processors (available since Nov '07) utilize unique materials (a high-k, dielectric) that are delivering industry leading performance / watt as measured by the industry's first and only standard benchmark, SPECPower

A "Tock" represents a more extensive architectural innovation (ex. Intel Core Microarchitecture) introducing new micro-architecture features and functionality fully utilizing the higher transistor count set up by the shrink. For Intel Xeon-based servers, the next "tock" is Nehalem. In addition to the new micro-architecture based on 45nm, a system re-design will incorporate next generation memory, I/O and virtualization technology for high performance, high bandwidth solutions compatible with today's leading software solutions

Listen to my podcast interview to learn more about the benefits of using today's products and the timing of next generation Intel technology featuring Nehalem. Is this information useful to you? If so ... how? Have any questions?

I'd be happy to hear from you. Chris

http://www.podtech.net/home/5105/45nm-and-beyond-with-christopher-peters

Kirk Skaugen - talking about data center of the future.

Server.Dude — Fri, 11 Apr 2008 20:01:54 GMT

Kirk was out at the Microsoft Server 2008 and talked about the "data center of the future". He discussed his thoughts on the data center of the future with some particularly interesting tidbits on the predictive enterprise, the world of Tera, emerging technologies and goings-on in Intel's IT shop.

Have you heard of the "predictive enterprise".? If you want to know more let me know as it is a very interesting topic.

50W Quad-Core: How would you use them?

C_Peters — Tue, 25 Mar 2008 18:09:14 GMT

Today, Intel launched 50W low power versions of the 45nm Quad-Core Xeon processors (the L5400 series).
The 2 new SKUs are listed below:

Quad-Core Xeon L5420 2.50 GHz, 12MB L2, 1333MHz
Quad-Core Xeon L5410 2.33 GHz, 12MB L2, 1333MHz

These products offer IT and business users 2 primary benefits:

45nm 50W quad-core brings 25% improved performance over previous generation 65nm 50W quad-core processors
They also run 30W cooler than mainstream 80W quad-core processors delivering the same performance at the same frequency.

We have seen strong interest for these 50W quad-core products and I'd like to hear from you on where you would use low power quad-core and why?

NAND solid state disks, the server wave…

Tony — Mon, 17 Mar 2008 19:40:48 GMT

So what's Intel been doing with NAND based Solid State Disk (SSDs) since my blog on our next generation broadband video streaming demo (http://communities.intel.com/openport/blogs/server/2007/11/14/). Two things: 1) we're close to launching Intel's SATA based SSD products and 2) we've been engaging you to get more details on your usage models and value propositions. In the last few months, there have been a number of announcements for SSDs in server and enterprise storage applications (e.g. EMC: http://www.emc.com/about/news/press/us/2008/011408-1.htm) including a number of small startups offering solutions targeted for server deployments. Based on my discussions with you and looking at what's going on in the industry, here's my view of the value of SSDs in servers and how that maps to server usage models.

As a person who focuses typically on the end-users, SSDs are interesting because they weren't designed to specifically solve an end-user server problem. As I said in my previous blog "because we could", SSD largely exist "because they can". They are what Clayton Christensen would call a disruptive technology. As SSDs are considered for server based applications, I look at how SSDs as a technology can provide greater value when replacing server hard drives (HDDs) or server memory and then build possible usage models from there.

When comparing to HDD usage in servers, I start with the following:

Performance: SSDs can have much better random access performance as measured by higher IOPS, higher throughput and lower read/write latency. SSDs are typically achieving a least 10 times the number of IOPs as HDDs, at least 2-3 times better random access read rate and on the order of 10 times less read and write latency than HDDs. For random access performance, most SSDs blow the highest performing 15K RPM hard drives away.

Power: SSDs use lower power especially when compared to a disk is that is active (i.e. spinning). Given that for most server based applications, the hard disk is always active, this is especially significant. My general observation is that SSDs typically use less than 1/5th of the power of an active HDD. Here they look to be a key technology for making data centers more power efficient.

Cost: When comparing cost per Gigabyte, SSDs are higher priced. Given this, SSDs today are largely being considered for applications where storage IO is the bottleneck - where many hard drives can be replaced with just a few SSDs.

SSDs can be compared to DDR memory with the same three value vectors:

Performance: Unlike the SSD to HDD comparison, memory has higher throughput and lower latency than an SSD. When comparing SSDs to memory for server usages, the primary consideration looks to be latency. SSD reads and writes are on the order of 100s of microseconds. On the other hand, memory based reads and writes are typically less than 100 nanoseconds. Even so, for some applications (e.g. video on demand streaming) 100s of microseconds of latency looks to be acceptable.

Power: Like HDDs, when comparing active power usage, SSDs draw much less power than DDR memory as measure by watts per gigabyte. How much is dependent on how the application uses memory. But generally, SSDs looked to consume 1/10th of the power.

Cost: Unlike HDDs, when comparing cost per gigabyte, SSDs are significantly lower priced than DDR memory. Generally, I start with NAND based SSDs as being half the price of DDR based memory. Depending on the size of the SSD and the technology (whether Single Level Cell (SLC) or Multi Level Cell (MLC)) the difference can be much more.

One final vector to look at is the reliability of SSDs when compared to hard disk drives and memory. Going with just the MTBF numbers being published, SSDs look to be better than HDDs and just as reliable as memory. One area that generates confusion is how the write cycle limitations of NAND technology affect the life-time (as measured by MTBF) of SSDs for server applications. Getting into details on this is a good subject for a future blog. But based on discussions with you, I haven't encountered a server application where the write cycle limitation is the deciding factor in a deployment for SLC SSDs (at least for how we expect Intel's SSDs to perform). For many server applications, it's not the deciding factor for MLC SSDs either.

Using these value vectors, here are my generalizations for the SSD value for enterprise and portal applications:

Use SSDs for the server boot device. When compared to HDDs, SSDs enable faster boot (typically 30%), consume lower power, and are more reliable.
Use SSDs for high throughput, high IOP, low latency application storage. If storage IO is the application bottleneck, replacing with SSDs shifts the bottleneck back to CPU utilization. Example applications include video streaming, search query, and OLTP.
Use SSDs for building a high performance storage tier. Many applications have hot and cold (or long tail) data. By creating a storage tier, the solution cost of a deployment can be reduced significantly. Example applications include using SSDs for improving performance in a NAS or SAN (e.g. what EMC calls Tier 0) or to creating a high performance direct attached storage (DAS) solution (e.g an SSD optimized server).
Consider SSDs as a lower cost alternative to placing application data in memory. Many applications create memory based databases to achieve low latency access times. These applications create custom data structures, use RamDisks or rely on caching through the OS (e.g. SWAP). For many IO bound applications, memory is typically being used as a buffer for disk data. The lower latency and higher throughput of SSDs promise to require less memory for buffering while maintaining the quality of service objectives of the application.

Bottom line for servers today, SSDs look to be cost effective for applications where storage IO throughput and low latency are key. They move the application bottleneck from IO to back to CPU utilization. Get back to me on whether you agree and what additional usage models you're finding.

Which Xeon is right for me?

C_Peters — Sat, 08 Mar 2008 07:01:36 GMT

I recently found this simple animation that breaks down the Xeon processor family into bite-sized chunks and explains which Xeon-based servers are best suited to meet common IT and business needs.

I shared it last week when traveling with customers in Taiwan and it was well received.

What do you think of this video?