In case you haven’t heard, “cloud” discussions are here to stay and everyone has their own recommendations for you to start building your cloud environment, but which is best for you?  Intel has created the “Intel® Cloud Builders” program aimed at making it easier for you to build, enhance and operate cloud infrastructure.

The Intel® Cloud Builders site is a collection of Cloud Design architectures resources from all of the major vendors like Cisco, EMC, Dell, HP and IBM.  Once you understand your cloud requirements then you can filter through the architectures based on one or more of the following:

1) Usage Models

• Infrastructure as a Service (IaaS)
• Policy-Based Power Management
• Scale-out Storage
• Trusted Compute Pools
• Unified Networking
• Client-Aware (self-service)

2) Cloud Computing Categories

• Build and Simply Your (existing) Cloud
• Improve Efficiency
• Enhance Security

3) Preferred Ecosystem Partner (allows you to pick your preferred hardware or software vendor)

While the site provides useful information, it is still limited.  For example a search in “all Dell” within the Content Library returns 3 documents; “all Cisco” returns 1 document and “all HP” returns 2 documents.  I see really good potential for this site, but Intel and their Ecosystem Partners are going to need to provide more documentation.  I would also like to see Intel introduce a filtering category that allows you to choose between rack servers and blade servers. 

Overall, I would give the site a 3 out of 5, so if you are looking for a resource to help you with your cloud design, check out Intel® Cloud Builders at http://www.intelcloudbuilders.com/

It’s no surprise that Intel will be release a few new lines of CPUs this year, but in today’s post I thought I’d take a few minutes to highlight some of the details. 

Intel to Change CPU Naming Schema
In an effort to simplify things, Intel will be changing the naming schema for their upcoming CPU releases.  Starting with the product line names, in the near future the Intel Xeon 7000 will become “E7“, Xeon 5000 = “E5” and Xeon 3000 = “E3“.  This means instead of seeing “Intel Xeon 7600″, you’ll now see something like “E7 – 4860″ – but what does the “4860″ stand for.  That’s part two of the equation.  If you take a look at the decoder ring below, you will see that in the case of the E7-4860, it would be a 4 socket, Westmere EX system with a core frequency of 2.26GHz.

E7 Overview (Westmere EX)
The successor to the existing 4 socket Intel Xeon 7500 CPU will be known as the E7 (codename Westmere EX).  Building on the success of the Westmere EP architecture, this new generation of multi-socket offerings brings a few new features:

• up to 10 cores and 20 processing threads
• 30MB of last level cache (shared across all CPU cores)
• 32nm processor technology
• support for 32GB DIMMs
• 4 Intel QuickPath Interconnects
• 4 DDR3 memory interconnects
• drop-in compatibility with Xeon 7500 systems (this feature will be dependent upon the OEM manufacturer – not all will offer / support this feature.)

I don’t have the details on the specific models that Intel will be releasing when they announce in late Q2 of this year, but I expect to see variations from a 2 socket offering with a low frequency all the way up to an 8 socket offering with very high frequency.  With power ratings as low as 95 watts, I hope to see the E7 in a blade server form factor, but I haven’t gotten any word on that – yet.

E5 Overview (Sandy Bridge)
Probably the most anticipated release is the Intel E5 CPU, aka Sandy Bridge.  The two socket CPU space holds the largest market share in the x86 server space, and is the most commonly used platform for virtualization.  Although the release date of this platform isn’t until the very end of 2011, it has gotten a lot of press lately, primarily because it has hit the desktop/notebook space first in the largest CPU launch since the Pentium.  The new Intel i7 is indeed based on the Sandy Bridge CPU platform (although somewhat scaled back.)  Here are the features that we can expect to see in the Intel E5 (Sandy Bridge) server platform:

• Up to 8 CPU cores (and 16 threads)
• 4 memory paths supporting memory speeds up to 1600Mhz
• 24 DIMM slots (768GB max)
• 2 Intel QuickPath links

An additional enhancement to the next generation Intel 2 socket CPU that is expected to rollout with the release of the E5 later this year is the addition of new Intel AVX instructions.  Similar to the way the Pentium MMX worked back in the 90′s, the AVX instructions are designed to help the CPU do common tasks in fewer steps.  Intel AVX improves performance due to wider vectors, new extensible syntax, and rich functionality. This results in better management of data and general purpose applications like image, audio/video processing, scientific simulations, financial analytics and 3D modeling and analysis.   For details on the Intel AVX instructions, visit Intel’s site at www.intel.com/software/avx.

You have probably heard of IBM’s ruggedized BladeCenter offering, the BladeCenter T and HT but did you know there was another IBM blade server offering that meets MIL-SPEC requirements that is not sold by IBM?  As threats to the U.S. continue to grow  military and intelligence orgainzations need to collect, process and analyze vast amounts of data to inform real-time decision making.  Recent advances over the past 5 years in technology have spurred smarter, more powerful and more efficient means of defense but continued budgetary challenges force systems and technology planners to seek the a balance of high-performance computing power capable of running the volume and complexity of applications that today’s military requires with the reasonable price point the DoD expects.  This reality requires advanced technology that combines high performance, reasonable cost and flexibility in a form factor specifically designed to meet MIL-SPEC standards for deployment outside the traditional data center . 

Tracewell Systems (www.tracewell.com/rbs) has found the way to deliver the military what they need with the “Rugged Blade System” (RBS) based on COTS, or Commercial Off The Shelf, blade technology from IBM.  This is a huge benefit to the military as it offers all the flexibility of commercial blade technology that is seen today in a ruggedized form factor that can meet MIL-SPEC requirements.  By using commercial blade server technology from IBM, Tracewell is able to deliver server technology that offers the DoD consistent performance, flexibility and consolidation capabilities all within a form-factor-engineered package designed to meet MIL-SPEC requirements. 

According to a press release in late October, Tracewell stated that the Tracewell RBS performed very well at the Empire Challenge 10 (EC10) event essentially proving its capabilities on the battlefield.  The EC10 is a multinational intelligence, surveillance and reconnaissance (ISR) demonstration designed to showcase the role of technology in improving military strategy, interagency coordination and military decision making. According to the after-action EC 10 report, “Throughout the exercise, the RBS performed to specification, even when subjected to high temperatures due to a lack of air conditioning (A/C).”   

I recently had the opportunity to speak with Matt Tracewell, Executive Vice President of Tracewell Systems in November to inquire about their offering.  My first question was “why IBM?”  Interesting enough, they went with IBM in the beginning for their Cell Blade (the QS product.)  However, they’ve since moved toward HS22v and GPU blades.  IBM has created a unique program that enables Tracewell Systems the ability to design new products based on the IBM blade products without changing the blade products themselves.  This means the standard switches and blade servers offered by IBM will work without any alteration inside the Tracewell Systems RBS.  Below are a few snap shots of the 3-blade Rugged Blade System.  The rear of the Tracewell Systems 3-Slot Blade System Rugged Chassis (last image) shows a single power plug and 3 shock, vibration proof RJ-45 plugs that allow for a dust-free connection.  You’ll also see USB and KVM plugs in a unique, but MIL-SPEC form factor.  Future designs from Tracewell Systems will offer 5 and 9 slot designs with multiple legacy and high-speed switch offerings.

In my opinion, the biggest deal about this offering is that it provides our military and intelligence organizations the ability to get new technology like Power 7 CPUs from IBM or Sandy Bridge CPUs from Intel in a timely manner giving them the industry’s best technology to insure the safety of our country.  Go Team USA!

 Thanks to fellow blogger, M. Sean McGee (http://www.mseanmcgee.com/) I was alerted to the fact that Cisco announced on today, Sept. 14, their 13th blade server to the UCS family – the Cisco UCS B230 M1. 

This newest addition performs a few tricks that no other vendor has been able to perform.Offering 32 DIMM slots, 2 x Intel Nehalem EX (Xeon 6500 or Xeon 7500 Series CPU) and 2 x hot-swap drives, all within a half-width form factor.  Very impressive offering although I have to admit, I’m a little ticked off that I didn’t know about this from the Cisco team ahead of time.  If I had, I might have held off my previous blog post (http://bladesmadesimple.com/2010/08/the-best-blade-server-option-is-part1/)  Now I have to go back and update that too…

Anyway, Sean does a nice job comparing the soon to be released HP BL620c G7, the IBM HX5 + MAX 5 and the Dell PowerEdge M910 blade servers (see below), so I encourage you to go visit his blog post and read up on what’s new.  Here’s the post:

http://www.mseanmcgee.com/2010/09/the-cisco-ucs-b230-the-goldilocks-blade-server/

  Nice job, Sean.  Thanks for the solid write up.

Okay, I can’t hold back any longer – I have more rumours. The next 45 days is going to be an EXTREMELY busy month with Intel announcing their Westmere EP processor, the predecessor to the Nehalem EP CPU and with the announcement of the Nehalem EX CPU, the predecessor to the Xeon 7400 CPU.  I’ll post more details on these processors in the future, as it becomes available, but for now, I want to talk on some additional rumours that I’m hearing from IBM.  As I’ve mentioned in my previous rumour post: this is purely speculation, I have no definitive information from IBM so this may be false info.  That being said, here we go:

Rumour #1:  As I previously posted, IBM has announced they will have a blade server based on their eX5 architecture  - the next generation of their eX4 architecture found in their IBM System x3850 M2 and x3950M2.  I’ve posted what I think this new blade server will look like (you can see it here) and  I had previously speculated that the server would be called  HS43 – however it appears that IBM may be changing their nomenclature for this class of blade to “HX5“.  I can see this happening – it’s a blend of “HS” and “eX5″.  It is a new class of blade server, so it makes sense.   I like the HX5 blade server name, although if you Google HX5 right now, you’ll get a lot of details about the Sony CyberShot DSC-HX5 digital camera.  (Maybe IBM should re-consider using HS43 instead of HX5 to avoid any lawsuits.)  It also makes it very clear that it is part of their eX5 architecture, so we’ll see if it gets announced that way.

Speaking of announcements…

Rumour #2:  While it is clear that Intel is waiting until March (31, I think) to announce the Nehalem EX and Westmere EP processors, I’m hearing rumours that IBM will be announcing their product offerings around the new Intel processors on March 2, 2010 in Toronto.  It will be interesting to see if this happens so soon (4 weeks away) but when it does, I’ll be sure to give you all the details!

That’s all I can talk about for now as “rumours”.  I have more information on another IBM announcement that I can not talk about, but come back to my site on Feb. 9 and you’ll find out what that new announcement is.

This means it can hold 384GB of RAM using 8GB DIMMS.  This is huge for the virtualization marketplace, as everyone knows that virtual machines LOVE memory.  No other vendor in the marketplace is able to provide a blade server (or any 2 socket Intel Xeon 5500 server for that matter) that can achieve 384GB of RAM. 

So what’s Cisco’s secret?  First, let’s look at what Intel’s Xeon 5500 architecture looks like.

As you can see above, each Intel Xeon 5500 CPU has its own memory controller, which in turn has 3 memory channels.  Intel’s design limitation is 3 memory DIMMs (DDR3 RDIMM) per channel, so the most a traditional server can have is 18 memory slots or 144GB RAM with 8GB DDR3 RDIMM. 

With the UCS B-250 M1 blade server, Cisco adds an additional 15 memory slots per CPU, or 30 slots per server for a total of 48 memory slots which leads to 384GB RAM with 8GB DDR3 RDIMM. 

How do they do it?  Simple – they put in 5 more memory DIMM slots then they present all 24 memory DIMMs across all 3 channels to an ASIC that sits between the memory controller and the memory channels.  The ASIC presents the 24 memory DIMMs as 1 x 32GB DIMM to the memory controller.  For each 8 memory DIMMs, there’s an ASIC.  3 x ASICs per CPU that represents 192GB RAM (or 384GB in a dual CPU config.) 

It’s quite an ingenious approach, but don’t get caught up in thinking about 384GB of RAM – think about 48 memory slots.  In the picture below I’ve grouped off the 8 DIMMs with each ASIC in a green square (click to enlarge.)

Cisco UCS B250 ASICS Grouped with 8 Memory DIMMs

With that many slots, you can get to 192GB of RAM using 4GB DDR3 RDIMMs- which currently cost about 1/5th of the 8GB DIMMs.  That’s the real value in this server.

Cisco has published a white paper on this patented technology at http://www.cisco.com/en/US/prod/collateral/ps10265/ps10280/ps10300/white_paper_c11-525300.html so if you want to get more details, I encourage you to check it out.

The first blade server with the upcoming Intel Nehalem EX processor has finally been unveiled.  While it is known that IBM will be releasing a 2 or 4 socket blade server with the Nehalem EX, no other vendor has revealed plans up until now.  SGI recently announced they will be offering the Nehelem EX on their Altix® UV platform. 

Touted as a “The World’s Fastest Supercomputer”, the UV line features the fifth generation of the SGI NUMAlink interconnect, which offers up a whopping 15 GB/sec transfer rate, as well as direct access up to 16 TB of shared memory. The system will have the ability to be configured with up to 2048 Nehalem-EX cores (via 256 processors, or 128 blades) in a single federation with a single global address space.

According to the SGI website, the UV will come in two flavors:

SGI Altix UV 1000

Altix UV 1000  - designed for maximum scalability, this system ships as a fully integrated cabinet-level solution with up to 256 sockets (2,048 cores) and 16TB of shared memory in four racks.

Altix UV 100 (not pictured) - same design as the UV 1000, but designed for the mid-range market;  based on an industry-standard 19″ rackmount 3U form factor. Altix UV 100 scales to 96 sockets (768 cores) and 6TB of shared memory in two racks.

SGI has given quite a bit of techinical information about these servers in this whitepaper, including details about the Nehalem EX architecture that I haven’t even seen from Intel.  SGI has also published several customer testimonials, including one from the University of Tennessee – so check it out here.

Hopefully, this is just the first of many announcements to come around the Intel Nehalem EX processor.

By now I’m sure you’ve read, heard or seen Tweeted the announcement that Cisco, EMC and VMware have come together and created the Virtual Computing Environment coalition .   So what does this announcement really mean?  Here are my thoughts:

Greater Cooperation and Compatibility
Since these 3 top IT giants are working together, I expect to see greater cooperation between all three vendors, which will lead to understanding between what each vendor is offering.  More important, though, is we’ll be able to have reference architecturethat can be a starting point to designing a robust datacenter.  This will help to validate that an “optimized datacenter” is a solution that every customer should consider.

Technology Validation
With the introduction of the Xeon 5500 processor from Intel earlier this year and the announcement of the Nehalem EX coming early in Q1 2010, the ability to add more and more virtual machines onto a single host server is becoming more prevalent.  No longer is the processor or memory the bottleneck – now it’s the I/O.  With the introduction of Converged Network Adapters (CNAs), servers now have access to  Converged Enhanced Ethernet (CEE) or DataCenter Ethernet (DCE) providing up to 10Gb of bandwidth running at 80% efficiency with lossless packets.  With this lossless ethernet, I/O is no longer the bottleneck.

VMware offers the top selling virtualization software, so it makes sense they would be a good fit for this solution.

Cisco has a Unified Computing System that offers up the ability to combine a server running a CNA to a Interconnect switch that allows the data to be split out into ethernet and storage traffic.  It also has a building block design to allow for ease of adding new servers – a key messaging in the Coalition announcement.

EMCoffers a storage platform that will enable the storage traffic from the Cisco UCS 6120XP Interconnect Switch and they have a vested interest in VMware and Cisco, so this marriage of the 3 top IT vendors is a great fit.

Announcement of Vblock™ Infrastructure Packages
According to the announcement, the Vblock Infrastructure Package “will provide customers with a fundamentally better approach to streamlining and optimizing IT strategies around private clouds.”  The packages will be fully integrated, tested, validated, and that combine best-in-class virtualization, networking, computing, storage, security, and management technologies from Cisco, EMC and VMware with end-to-end vendor accountability.  My thought on these packages is that they are really nothing new.  Cisco’s UCS has been around, VMware vSphere has been around and EMC’s storage has been around.  The biggest message from this announcement is that there will soon be  “bundles” that will simplify customers solutions.  Will that take away from Solution Providers’ abilities to implement unique solutions?  I don’t think so.  Although this new announcement does not provide any new product, it does mark the beginning of an interesting relationship between 3 top IT giants and I think this announcement will definitely be an industry change – it will be interesting to see what follows.

UPDATE – click here check out a 3D model of the vBlocks Architecture.

(UPDATED 10/28/09 with new links to full article)

I received a Tweet from @HPITOps linked to Gartner’s first ever “Magic Quadrant” for blade servers.  The Magic Quadrant is a tool that Gartner put together to help people easily where manufacturers rank, based on certain criteria.  As the success of blade servers continues to grow, the demand for blades increases.  You can read the complete Gartner paper at http://h20195.www2.hp.com/v2/getdocument.aspx?docname=4AA3-0100ENW.pdf, but I wanted to touch on a few highlights.

Key Points

• *Blades are less than 15% of the server marketplace today.
• *HP and IBM make up 70% of the blade market share
• *HP, IBM and Dell are classified as “Leaders” in the blade market place and Cisco is listed as a “Visionary” 

What Gartner Says About Cisco, Dell, HP and IBM

Cisco
Cisco announced their entry into the blade server market place in early 2009 and as of the past few weeks began shipping their first product.  Gartner’s report says, “Cisco’s Unified Computing System (UCS) is highly innovative and is particularly targeted at highly integrated and virtualized enterprise requirements.”  Gartner currently views Cisco as being in the “visionaries” quadrant.  The report comments that Cisco’s strengths are:

• they have a  global presence in “most data centers”
• differentiated blade design
• they have a cross-selling opportunity across their huge install base
• they have strong relationships with virtualization and integration vendors

As part of the report, Gartner also mentions some negative points (aka “Cautions”) about Cisco to consider:

• Lack of blade server install base
• limited blade portfolio
• limited hardware certification by operating system and application software vendors

Obviously these Cautions are based on Cisco’s newness to the marketplace, so let’s wait 6 months and check back on what Gartner thinks.

Dell
No stranger to the blade marketplace, Dell continues to produce new servers and new designs.  While Dell has a fantastic marketing department, they still are not anywhere close to the market share that IBM and HP split.  In spite of this, Gartner still classifies Dell in the “leaders” quadrant.  According to the report, “Dell offers Intel and AMD Opteron blade servers that are well-engineered, enterprise-class platforms that fit well alongside the rest of DelI’s x86 server portfolio, which has seen the company grow its market share steadily through the past 18 months.”

The report views that Dell’s strengths are:

• having a cross-selling opportunity to sell blades to their existing server, desktop and notebook customers
• aggressive pricing policies
• focused in innovating areas like cooling and virtual I/O

Dell’s “cautions” are reported as:

• having a limited portfolio that is targeted toward enterprise needs
• bad history of “patchy committment” to their blade platforms

It will be interesting to see where Dell takes their blade model.  It’s easy to have a low price model on entry level rack servers, but in a blade server infrastructure where standardization is key and integrated switches are a necessity having the lowest pricing may get tough.

IBM
Since 2002, IBM has ventured into the blade server marketplace with an wide variety of server and chassis offerings.  Gartner placed IBM in the “leaders” quadrant as well, although they place IBM much higher and to the right signifying a “greater ability to execute” and a “more complete vision.”  While IBM once had the lead in blade server market share, they’ve since handed that over to HP.  Gartner reports, “IBM is putting new initiatives in place to regain market share, including supply chain enhancements, dedicated sales resources and new channel programs.“ 

The report views that IBM’ strengths are:

• strong global market share
• cross selling opportunities to sell into existing IBM System x, System i, System p and System z customers
• broad set of chassis options that address specialized needs (like DC power & NEBS compliance for Telco) as well as Departmental / Enterprise
• blade server offerings for x86 and Power Processors
• strong record of management tools
• innovation around cooling and specialized workloads

Gartner only lists one “caution” for IBM and that is their loss of market share to HP since 2007.

HP
Gartner identifies HP as being in the farthest right in the October 2009 Magic Quadrant, therefore I’ll classify HP as being the #1 “leader.”  Gartner’s report says, “Since the 2006 introduction of its latest blade generation, HP has recaptured market leadership and now sells more blade servers than the rest of the market combined.”  Ironically, Gartner list of HP’s strengths is nearly identical to IBM:

• global blade market leader
• cross selling opportunities to sell into existing HP server, laptop and desktop customers
• broad set of chassis options that address Departmental and Enterprise needs
• blade server offerings for x86 and Itanium Processors
• strong record of management tools
• innovation around cooling and virtual I/O

Gartner only lists one “caution” for HP and that is their portfolio, as extensive as it may be, could be considered too complex and it could be too close to HP’s alternative, modular, rack-based offering.

Gartner’s report continues to discuss other niche players like Fujitsu, NEC and Hitachi, so if you are interesting in reading about them, check out the full report at 

http://h20195.www2.hp.com/v2/getdocument.aspx?docname=4AA3-0100ENW.pdf.  All-in-all, Gartner’s report reaffirms that HP, IBM and Dell are the market leaders, for now, with Cisco coming up behind them.

Feel free to comment on this post and let me know what you think.

BL2x220c G5 (2 server "nodes" shown)

HP’s BladeSystem server offering is quite extensive – everything from a 4 CPU Intel blade to an Itanium CPU blade, however their most well hidden, secret blade is their BL2x220c blade server.  Starting at $6,129, this blade server is an awesome feet of design because it is not just 1 server, it is 2 serversin 1 blade case – in a clam shell design (see below).  This means that in a HP C7000 BladeSystem chassis you could have 32 servers!    That’s 64 CPUs, 256 CORES, 2TB of RAM all in a 10U rack space.  That’s pretty impressive.  Let me break it down for you.  Each “node” on a single 2 node BL2x220c G5 server contains:

• Up to two Quad-Core Intel® Xeon® 5400 sequence processors
• Up to 32 GB (4 x 8 GB) of memory, supported by (4) slots of PC2-5300 Registered DIMMs, 667 MHz
• 1 non-hot plug small form factor SATA or Solid State hard drive
• Embedded Dual-port NC326i Gigabit Server Adapter
• One (1) I/O expansion slots via mezzanine card
• One (1) internal USB 2.0 connector for security key devices and USB drive keys

You may have noticed that this server is a “G5″ version and currently has the older Intel 5400 series processors.  Based on HP’s current blade offering, expect to see HP refresh of this server to a “G6″ model that will contain the Intel® Xeon® 5500 series processors.  Once that happens, I expect for more memoryslots to come with it, since the Intel® Xeon® 5500 series processors have 3 memory channels.  I’m guessing 12 memory slots “per node” or 24 memory slots per BL2x220c G6.  Purely speculation on my part, but it would make sense.  

Why do I consider this server to be one of HP’s best hidden secrets?  Simply because with that amount of server density, server processing power and server memory, the BL2x220c could become a perfect virtualization server.   Now if they’d only make a converged network adapter (CNA)…