A number of months ago, I penned a blog about how HP's EDS acquisition left Dell in an IT services lurch. One of the side points in this blog was Dell's lack of enterprise credibility.... and Dell being a potential suitor to buy Sun Microsystems (It's Your Turn Dell). Fast-forward to this week, where Sun announced they would lay off 6,000 employees. Also notice Sun's market capitalization is now down to $3.1B US. If ever there were a time for Dell to scoop up Sun, this is it.

Why would Dell buy Sun? Isn't this madness? Doesn't Dell have enough problems of it's own? Yes, they do. But let's ask ourselves how Dell got into this position (and not just blame it on the current economic conditions).

The crux of my blog went back to a time when Compaq -- lacking enterprise credibility -- was in a similar situation to Dell. Here's an excerpt:

Dell’s product portfolio is lacking the power to reach into some enterprise accounts. This situation reminds me of a [compay wide] meeting at Compaq (circa 1994). The gist from executive management was that Compaq (a $20 Billion dollar company at the time) could not compete in some accounts because it did not have enterprise products necessary to win the [entire] account. In other accounts, it could only win a portion of the IT budget (those tied to x86 servers and small business storage). Compaq executives realized – correctly – that the Compaq brand lacked enterprise credibility; they needed to acquire the technology and talent necessary to compete, rather than building it internally over several years. As a result, they acquired Tandem (Non-stop platform) and DEC (enterprise services, storage, workstations, VAX, 64-bit computing, top-notch compiler team…the list is so long), which gave Compaq the goods and brand recognition to compete at an enterprise level.

Dell needs to do the same. They’re basically at the same point Compaq was in 1994. The Dell brand is lacking the enterprise punch to compete. And with more HP “feet on the street” than ever, Dell will increasingly be marginalized -- pushed out of accounts where they don’t have the product portfolio to “own the entire account”. They need to acquire the technology rather than slowly building internally/organically.

The blog went on to say that although Dell had some products in the enterprise space, they needed to beef up their server and storage enterprise credibility and that acquiring Sun would help Dell attain the credibility they need rather than waiting for Intel to push mini-computers out of the market using the x86 architecture.

Although x-86 servers make up a majority of the server market (especially in terms of units sold), for some applications, customers require systems that have a higher class of availability and performance. In this area, IBM and HP have products at the “mainframe” level (Z-Series and Superdome respectively) and the “workstation” level (P-Series/i-Series and Non-Stop/HP-UX respectively). Dell doesn’t. This problem is harder for Dell to solve. Perhaps Dell can wait for AMD and Intel to solve this product gap problem for them through the future scalability of the x86 server architecture. But another possible scenario is for Dell to acquire Sun (which could be had at a good price). This may sound like madness, but so did the HP/Compaq merger when Carly Firoina and Michael Capellas announced the plan in 2001. Today, the HP/Compaq merger is widely regarded as the right move because it gave HP the product portfolio and services it needed to compete with IBM in the enterprise. Dell needs the product punch and the enterprise brand credibility that Sun can provide.

Little did I know that the price would get much, much better.

Dell's business model has always been about draining profit pools. Dell jumps into a market when the competition has created a market with significant demand on a profit rich product. Dell MO is to come in at a lower price point, drive up tons of volume, and push the competition out of the market. At Dell, they call it "the curve". "The Dell curve" is drilled into the heads of Dell-ians from the day they walk through the front door. But many question the value of such a business model. What happens when there are no more profit pools to drain? What happens when margins are so slim that quality and support suffer? What perception does "low-cost leader" do to the brand? In enterprise circles, price is only one concern...availability, reliability, scalability, and management can be just as -- if not more -- important.

The margin-rich enterprise arena is where Sun excels. Sun has the credibility in enterprise hardware, operating systems, software, and several other technologies. The enterprise is Sun's home turf and they bring a truck-load of loyal enterprise customers.

The question is: would Dell make this move? It's a gamble to be sure. Dell would have to change their spots -- the way they operate, their mindset. Enterprise products are not made without investments in research.

From another viewpoint, Dell has the enough cash to make such a purchase. As of Friday, Dell had approximately $9B US in cash on hand, with about $2B US in debt. Sun, on the other hand, has $2.3B US in cash and $1.2B US in debt. And...one could make the argument that Dell should wait until the market recovers; Dell is in a better position to recover than Sun. But Dell has to think in terms of the compeition too. Dan Nosowitz from Gizmodo wrote an interesting blog on a CNET article concerning which PC company was best positioned to weather the current economic conditions.

I mean, what if HP or IBM bought Sun? What would Dell’s options be if that happened? With Sun off the market, who else could Dell buy to get into the enterprise game? Basically, no one. They’d have to settle for being a smaller player in the enterprise – hoping to grow the market organically (which could take years or never happen). HP buying Sun would leave Dell in an enterprise lurch they way HP's EDS acquisition did for services.

Dell missed their opportunity to buy EMC several years back and now they are kicking themselves. They should not make the same mistake with Sun. If HP bought Sun, Dell’s best option would probably be to move down market toward consumer devices. Meaning: become the best consumer gadget device company in the land because the enterprise space would be a much more difficult market to capture (Dell probably wouldn’t “give up” in the enterprise, but the road will only continue to get harder for them).

However, being a consumer device company would be difficult road too because 1) the margins are slim. 2) Discretionary consumer spending is much more sensitive to market downturns. 3) There is lots of competition from Apple, Sony, etc, where customer brand loyalty is strong. It’s much easier to drain profit pools where profit margins exist.

Dell has to make some hard choices. But, opportunity arises amid chaos.

[posted by: Drue Reeves]

In the past couple of months, both Microsoft and VMware have been wary of defining their new platforms as an “operating system”. Microsoft was adamant that Azure isn’t an operating system, while VMware did use the term but hedged by saying that it wasn’t really the same thing as a conventional operating system. So the question arises "is there such a thing as a cloud operating system?". To answer that question we need to look at what a traditional operating system provides and compare it with the functionality that is needed to create a "cloud". Traditional operating systems are something of a moving target in that they have evolved over time and the definition has become somewhat clouded. But for the most part people would agree that the operating system provides:

1. Management of hardware resources like processors, memory and I/O interfaces to abstract the underlying hardware details from applications.
2. Scheduling of application execution to allow multiple applications to share the same hardware.
3. Application programming interfaces (APIs) to allow inter-process communication and other fundamental constructs needed by application developers.
4. Management interfaces to simplify installation and update of applications and operating system components.

These features all operate at a single system level (though clustered systems have extended the concepts to some degree) and require the operating system to “understand” the individual hardware components within the server.

A “cloud operating system” has to operate at macro level to control the operation of multiple servers in the cloud, which means creating functions that are analogs of the micro-level functions provided by a traditional operating system:

1. You can’t just plug a server into the cloud and make it useful, it’s just a bunch of components, so there has to be some software installed on each server to control it. For example Microsoft’s Azure system will install a hypervisor onto any server in the cloud (for more details see http://www.vinternals.com/2008/11/microsoft-azure-infrastructure.html). This provides the bare minimum of functionality on each server.
2. Shared resources like storage have to be managed and presented to applications in the cloud, the vStorage component of VMware’s VDC-OS (for more details on vStorage see http://virtualgeek.typepad.com/virtual_geek/2008/09/so-what-does-vs.html).
3. Applications have to be scheduled in the cloud, so that quality of service can be maintained by ensuring that nobody hogs all the resources in the cloud.
4. Depending on the cloud implementation there maybe APIs for application developers. Examples of cloud platforms that provide interfaces for application developers include both Microsoft’s Azure and Google’s App Engine. In contrast, VMware’s VDC-OS doesn’t provide application developers with interfaces (for more discussion on this see my previous blog entry “Waiting For The Other Shoe to Drop”
5. Management interface to assist in managing the cloud and deploying applications into the cloud.

So the cloud platforms of the future must have functions that are similar in many ways to a traditional operating system. To a degree, the classification of these new cloud platforms is irrelevant, ultimately, if vendors and customers are comfortable with calling them cloud operating systems, then that’s what they’ll end up being called.

Posted by: Nik Simpson

The last time I blogged about SSD performance I had a Intel MLC based SSD,  intended mostly for laptop or read intensive applications. Looking back at that blog, I reported pretty decent performance numbers with the X25-M Intel drive.

Christmas came early this year for me - I recently received several Intel X25-E enterprise SLC SSDs for evaluation. As an analyst I normally don't get the chance or have the time to get down and dirty, but this opportunity was too good to pass up. Besides, my career has been spent developing products and diving into details. Its hard to leave that legacy behind while looking at a box of SSDs just begging to be run through their paces. As, apparently, the only analyst to receive these drives, I felt obligated to take them for a ride and see if my previous enthusiasm was justified.

Lets get right to it:

I ran tests, using IOMeter on a 2.66GHz quad Core 2 Intel CPU, 45nm, 12MB L2 cache, with a 1333 front side bus, 4G memory, SATA II 300MB/s ports. The tests were run on a single SSD, both the M and E version, as well as the E version in a 4 drive RAID 5 configuration. Unfortunately, I don't have a decent RAID adapter (hint) so I used the onboard NVidia MediaShield RAID function. 

While I have more data, for simplicity I've plotted IO transaction rates for 512, 4096 and 32768 block sizes for random reads and writes. Using all random reads and writes provides significant stress on the SSD and is a good reference point for comparison to HDD performance.

Take a look at the graph:

In the graph, I plot the transactional performance of the X25-M, X25-E, X25-E in RAID 5 and a SATA HDD as a function of block size.

Its worth pointing out that the tests I ran are far from real world, but they do highlight performance under extreme conditions. Measuring performance can be a tricky business, but I believe the tests I’ve run are a good reference point and easily repeatable – except for a weirdness that I’ll point out in a few…

Take a close look at the results. The performance for the X25-E is very compelling. For random reads, the X25-E's (as a single drive and RAIDed) performance tops out around 12,000 IOPs as does the X25-M. You'll need to look closely to see the plotted lines as they overlap at the top of the graph. I suspect that the drives are capable of much more and are bottlenecked by the upstream motherboard and driver stack limitations. I didn't spend much time tuning my system so I suspect that the read number could be far higher. In any case, the values leave the poor SATA HDD in the dust.

The random write performance is equally compelling for the X25-E, operating far faster than the X25-M and making the HDD look like a stone.

The "X25-E RAID5 - Write" test, using 4 disks, stands out like a turkey in a chicken ranch. The RAID performance is actually worse than a single disk. Hmm, why is that?

When doing writes in a RAID 5 configuration, an XOR operation is required (not so when reading). Since the RAID function on my motherboard is driver based, no doubt my system is the bottleneck. This limitation does point out the stress placed on RAID adapters when dealing with high transaction rate devices. Most RAID adapters are best suited to dealing with single threaded devices (e.g. hard disks) operating at hundreds of IOPs not thousands of IOPs as SSDs can do. I'll have to wait to get my hands on a decent RAID adapter (hint number 2) before this can be explored further.

but there is some weirdness, look at the following graph:

As I prepared to collect performance data, I ran the random 4k block write test a few times. I noticed that the result varied over time and depended on the state of the SSD before the test was run. That's weird. With a hard disk, performance is very predictable and constant over time. Apparently not so for an SSD. I think we knew this but the graph proves the point. Before the test, I had conditioned the X25-E with 64K random block writes. Not scientific, but the results shown in the above graph are curious none the less. The random write performance varied four to one over the period of 30 minutes where I collected performance data at 5 minute intervals.

While much more performance testing and analysis is needed, such as the examination of latency values, I'll leave that to others with more time on their hands.... 

The performance of the Intel X25-E is remarkable compared to a hard disk. Unfortunately, the unexpected performance variability was a surprise and adds a new dimension to interpreting performance data.

Oh, and btw, the X25-E hardly got warm to the touch throughout the testing. So while I don't have a way to measure power, the X25-E clearly uses far less power than my SATA HDD that I can use as a donut warmer.

So this brings up a good point, and I'll end the blog on this note:

The industry needs a standard way to test SSDs. Period.

Please feel free to comment. 

Posted by Gene Ruth

Miscommunication: If you can't understand me, I'll repeat it slower and louder until you do

When I think of the cloud, I think of all of the companies out there trying so hard to get their message heard, and at the same time, trying to not to miss this phenomenon, that the flood of information is muddying the water for many people. So, instead of a long, drawn out description of my feelings on the subject, I decided that Adam Sandler's Cajun Man is a better way to describe what I think reflects the feelings many people have regarding the cloud...and how we at the Burton Group view the cloud.

When the cloud first emerged it seemed: Magnification. Amplification. Attraction. Concentration.

This led to further feelings: Over-promotion. Disorganization. Confusion. Obfuscation. Irritation. Frustration. Caution.

So, feeling frustrated with the situation, I began to explore the subject a bit more and through researching existing solutions, comparing vendors strategies, talking with Ken Oestreich, and talking with colleagues from the Burton Group like Anne Thomas Manes, Chris Howard, Mike Gotta, Jack Santos, and the DCS team, Anne and I drew this model (the whole stack represents different parts of the cloud):

After lots of internal debate we finally had: illumination. Definition. Disambiguation. Rationalization. Elation! Celebration! Congratulation.

I actually believe this is a high-level conceptual diagram, perhaps reference architecture even, of the cloud...because each layer can build upon the other. Platform as a service providers like Oracle can build their cloud strategy on top of System Infrastructure as a Service providers like Amazon's EC2. While at the same time, each step in the stack can/may stand on its own.

But then I began to think about the issues that come with the cloud...things like security, trust between IT organizations and the cloud, lack of API to initiate workloads in the cloud, workload mobility, storage and network state when things move, high availability and business continuity of cloud providers, service level agreements, etc, etc, etc.

No Standardization. Miscommunication. Slow-migration. Infatuation.  Deflation. Depression.

So now, we have to ask: what are the things that can help enable the cloud? Because clearly, there are obstacles to overcome. I'll post more on these later, but a few key cloud standards would be: Open virtual machine format (OVF) to enable VM/workload mobility between clouds, Locator/ID Separation Protocol (LISP) might be needed, a "cloud" API to help engage cloud providers, XML definition for SLAs, to name a few.

So now, at least we have a definition for the cloud and high-level architecture to build upon and flush out. Or, in Cajun Man terms: Clarification. Anticipation. Cooperation. Ratification? Reverberation? Validation.

[posted by Drue Reeves]

For the past two years I have been listening to security and compliance auditors who routinely complain that they need help with effectively auditing for compliance (e.g., regulatory, security policy) in virtualized environments. During that span, I'd often hear auditors tell me the following:

I don't know where to start.

What within the virtual infrastructure constitutes a trusted security boundary?

Are the vendors in the virtualization space and the standards bodies (e.g. PCI) doing anything to help?

That being said, I have taken auditor feedback (both general and specific) to the major virtualization vendors and asked them if they could push the ball forward and throw the auditors a life line. Unfortunately, a senior executive at one prominent vendor told me:

Auditing is an internal issue that is unique to all organizations, and we have no place in this area.

When the executive made that statement, I told him why I disagreed and tried to clarify my position, again stating that the virtualization vendors needed to take the ball to the engage the standards bodies and also to provide the clarity that the auditors required. He still disagreed.

Hope is not lost for the auditing community, as VMware today announced that it is joining the PCI standards council as a participating organization, and the launch of the VMware Compliance Center Web site. The Compliance Center includes a very nice list of white papers that I think auditors will find helpful. VMware - great job. With this announcement, I think Christmas just came early for many in the auditing community. Now for VMware's competitors, I'm once again going to repeat my request to you - please get serious about providing guidelines and clarity for security auditors. They want your help. Without it, some will inevitably revert to enforcing full physical isolation within their organization's virtual infrastructure, something which reduces consolidation density and undermines your TCO arguments. What do you say? If you're serious about being a production-class virtualization platform, you need to publicly demonstrate how you are serious about security and compliance. The ball's in your court.

Posted by: Chris Wolf

I've been traveling quite a bit lately, so it's been hard to keep up with the blogs that I normally frequent. Today I played catch-up with Mike Dipetrillo's blog, which contained an interesting post on VMware's Distributed Power Management (DPM), an "experimental" feature in VMware's VI 3.5 software. This is an interesting concept, and one that competitors such as Virtual Iron offer as well. While such features make for a nice story and blog post, I have to question how relevant they are to the typical enterprise. Don't get me wrong. Power management is critical and the virtualization platform vendors will have to play a role in adding power management to the hypervisor; however, I'm not convinced that fully shutting down physical hosts is the solution. Sure the mobility offered by virtualization mitigates the risk associated with component failure that may result from frequent power cycles - if one physical host doesn't come up, the VMs can run on the remaining nodes in the cluster. But is the approach offered by DPM a pill most enterprises are ready to swallow?

This year alone, I have asked hundreds of IT folks about power management and I can count on one hand those that would allow software to dynamically shut down and power up their production systems. Why? Practically every one of them has cold booted a server and had it not come back up. So the idea of scheduling such an activity to occur daily scares the (insert your favorite adjective here) out of them. Driven by these concerns, Burton Group approached every major server independent hardware vendor (IHV) this year and asked them if they had conducted any testing on the impact of distributed power management (shutting down servers nightly) and mean time between failure (MTBF). Across the board, the answer was "No."

Some IHVs aren't too interested in even testing such a scenario because they don't think it will ever fly in most enterprises. Instead, they feel that adding more power management features (e.g. powering down unneeded CPUs, memory, or PCI devices) to their server platforms is the right path to take. Of course, this means that the hypervisor vendors will need to update their software to take advantage of such features. Also, the IHVs will still need to conduct MTBF testing to ensure that any new power management features do not significantly degrade MTBF. As embedded hypervisors (e.g. ESXi, XenServer OEM) continue to evolve, we'll hit a time where physical drives are no longer needed in servers. Instead, the hypervisor will simply load from flash. Getting the hard disk out of the server will improve power efficiency, but we also need better power management between the hypervisor and server too.

Microsoft has already announced that advanced power management will be included in the Hyper-V update coming in Windows Server 2008 R2. VMware, Citrix, and Virtual Iron (among others) will need to follow a similar path. Until we have advanced power management in the server and hypervisor, and have MTBF tests that allow enterprises to adopt such features with confidence, let's hold off on propping up science projects features like DPM. Using such features in development, test, or training environments may make sense if you feel the good (improved energy efficiency) outweighs the bad (reduced server or component life). In production environments, stay away from features such as DPM until your preferred IHV will stand behind a particular power management solution, and has the test data to back it up.

Posted by: Chris Wolf

I've been traveling quite a bit lately, so it's been hard to keep up with the blogs that I normally frequent. Today I played catch-up with Mike Dipetrillo's blog, which contained an interesting post on VMware's Distributed Power Management (DPM),... Chris Wolf

In the past couple of months, both Microsoft and VMware have been wary of defining their new platforms as an ???operating system???. Microsoft was adamant that Azure isn???t an operating system, while VMware did use the term but hedged by... Nik Simpson

Several news agencies are reporting that Jerry Yang is out as CEO and taking on the role of Yahoo Chief (whatever that means). Including: Financial Times, CNBC, Fortune.

You had to see this one coming.

Yahoo's failed strategy is not only an inability to compete in the ad revenue laden search engine business, it was also a lack of vision when it comes to new potential revenue streams (i.e. the cloud). In fact, Martin Pyykkonen from Wunderlich Securities was interviewed on CNBC stating that Yahoo! has several good assets but needed to put those technologies to work and better monetize their assets.

I agree. Although search ad revenue is good, but is it enough anymore? The Internet isn't a research tool, it's a business medium. Yahoo! has the tools and people to make their business the place where business is conducted. Here are some steps that Yahoo!  needs to make to compete in their market:

• Offer cloud services: In the same vein that Google and Salesforce have offered software and application platforms as a service, Yahoo can do the same. And I'm not just talking about about email. Yahoo! should enable a developer network to build applications and run them in Yahoo's environment (of course, they may not have the data centers to drive such a model).
• Offer data services: Yahoo has to start using their search engine to reveal more than just what a simple search can tell. While they do this today (top searches for XYZ), they should use their data services to help solve larger problems such as predict flu outbreaks (ala Google) based on search locations; in other words use the data to solve big problems and they'll drive business their way.
• Partner with key players: Microsoft would have been a good start. Could Yahoo! offer Microsoft Azure in their data center? Could Yahoo! partner with AT&T to offer phones, or with Dell to offer music? One might argue that because Yahoo! is cash poor (compared to Google), they have to partner to stay competitive. Yahoo! doesn't have the cash to do it all.

Now the burning question on everyone's mind is does this reopen the path toward a Microsoft acquisition? Time will tell.

[posted by: Drue Reeves]

Several news agencies are reporting that Jerry Yang is out as CEO and taking on the role of Yahoo Chief (whatever that means). Including: Financial Times, CNBC, Fortune.You had to see this one coming.Yahoo's failed strategy is not only an... Burton Group Burton Group

A number of months ago, I penned a blog about how HP's EDS acquisition left Dell in an IT services lurch. One of the side points in this blog was Dell's lack of enterprise credibility.... and Dell being a potential... Burton Group Burton Group

For the past two years I have been listening to security and compliance auditors who routinely complain that they need help with effectively auditing for compliance (e.g., regulatory, security policy) in virtualized environments. During that span, I'd often hear auditors... Chris Wolf

For the past two years I have been listening to security and compliance auditors who routinely complain that they need help with effectively auditing for compliance (e.g., regulatory, security policy) in virtualized environments. During that span, I'd often hear auditors... Chris Wolf

Two interesting things happened in the computer storage biz on Monday: Sun announced their new "Amber road" storage products and Violin Memory, a small startup, introduced a high performance pizza box storage appliance. Both these products are leveraging NAND flash SSD technology. Both in interesting ways.

BAM, new era...sorry couldn't resist.

It would be easy to go all gaga over these products but caution is advised. Both are innovative in their own right, both challenge the status quo of the data center class storage system business. These are innovative products. No matter what my comments to follow are, keep this in mind: these products are integrating new technologies in new ways and therefore, regardless of the technical prowess of the suppliers, caution should be exercised before inserting these products into a data center on a large scale.

Try'em to verify'em.

In my past blogs about SSDs, I've mentioned that flash SSDs are about transactional performance not capacity.  I stated that capacity will have to wait until flash memory density increases and pricing decreases dramatically - we will be waiting for awhile. So, I went on to suggest that a storage system based on SSDs, to be well rounded, must offer high performance but solve any capacity shortfall by including high capacity SATA disks. To make that workable, some magic is needed to move data around appropriately to match the data's dynamics.

That's what the new Sun storage product claims to do.

Sun, by leveraging their open source ZFS file system, with some crucial tweaks, marries SSD technology for performance and SATA hard disk technology for capacity. Compared to an all HDD system, Sun claims up to 3x read transactional performance, 5x less power, at about the same cost.

Not bad.

Turns out Sun uses SSDs tailored both for write performance to handle an internal logging function and then read optimized SSD to act essentially as a really large cache. All wrapped around their open-source ZFS file system hidden within the storage subsystem. Sun is demonstrating technology leadership by tightly integrating SSD technology into a complete storage subsystem - yes others have done a pluggable replacement for a HDD, but that's fairly obvious and less then optimal. And there have also been some demonstrations such as IBM's Quicksilver science experiment based on Fusion-io, but no significant shipping product.

There are certainly other nice features in the Sun "Amber Road" products such as an improved management interface, analytics and such but blah, blah, blah. The industry expects those things, they are the price of entry and are the nuts and bolts of any system. Of course you need good pricing, support, quality and the like - that's all good, but its expected. If a vendor does not live up to the expectation - they get voted off the island - fast.

Sun has a window of opportunity here to make some market share gains, before other major vendors show up to the party. Its on you Sun. Price the product to move, forget premium pricing. Get support right, and accounts will be won. Don't forget: others will arrive at the SSD party soon as well. Grab market share while you can. Show customers how Sun is setting a new price-performance bar only reachable with SSD technology. Game on. Watch your back, I expect strong competition in the SSD space over time, the vendors who don't react are no worry since they will not survive in the long run.

Back to Violin. Violin introduced a 2u (that's about 2 pizza boxes) flash based storage appliance. While this is not an holistic performance and capacity solution, it does offer an excellent example of what happens when you take the "D" out of SSD. No longer constrained by the HDD form factor, the Violin 1010 uses memory card like flash modules that plug into a motherboard. As part of the design, there is a RAID like redundancy for the flash modules with hot plug support in case one fails - but I gotta admit, I wouldn't touch the thing while its running. Find an intern to do it and if things go wrong make the intern the scape goat.

For those running transactional applications, like a database, this product could be a godsend. But I fear the pricing may be too high and you do need to accept working with a newbie in the space. The Violin 1010 attaches directly to PCIe (it also does FC and Ethernet) . PCIe is needed to achieve high iops - fibre channel and scsi in general add too much latency but that's the subject of a future blog.

The Violin product is interesting on its own but consider: Combine the Violin 1010 with a bunch of 1TB SATA hard disks and Sun's open storage software with ZFS. Add in a few tweaks for auto-tiering, do some soul searching about pricing and you could have an awesome product. 

So where is all this SSD technology going? Into data centers, sooner than anyone has imagined.

Two interesting things happened in the computer storage biz on Monday: Sun announced their new "Amber road" storage products and Violin Memory, a small startup, introduced a high performance pizza box storage appliance. Both these products are leveraging NAND flash... Gene Ruth

Two interesting things happened in the computer storage biz on Monday: Sun announced their new "Amber road" storage products and Violin Memory, a small startup, introduced a high performance pizza box storage appliance. Both these products are leveraging NAND flash... Gene Ruth

Two interesting things happened in the computer storage biz on Monday: Sun announced their new "Amber road" storage products and Violin Memory, a small startup, introduced a high performance pizza box storage appliance. Both these products are leveraging NAND flash... Gene Ruth

This week, Microsoft announced it’s cloud platform Windows Azure and one thing is for sure, it looks nothing like VMware’s Virtual Data Center OS initiative (VDC-OS) announced at last month’s VMworld conference (for reference, see Chris Wolf’s Keynote Blog). The two approaches represent fundamentally different views of how the cloud should be built and what form applications will take.

VMware’s approach is really an evolution of virtual server environment we know today. A cloud data center running VDC-OS will consist of several components:

• Servers - lots of ‘em. Companies are already building giant cloud data centers which hold hundreds of thousands of server and consume megawatts of energy.
• Storage – by the terabyte: Storage will come in a variety of forms and will likely include NAS, SAN and direct attached disk.
• Networks - thousands of ports: Networks tie everything together and connect the cloud the outside world.
• Software layer - virtualize the hardware: Provides a hypervisor, virtual storage plus storage services like thin-provisioning, virtual networks to manage connectivity, provisioning and deployment for virtual machine images.
• Workloads – where the work gets done: At its simplest a workload is simply a virtual machine containing an operating system (i.e. Windows or LINUX) and the application. To handle more complex multi-tier applications (say a web server, database server and a application load balancer) administrators will create workload containers that consist of multiple virtual machines with connectivity, service levels, and other critical information defined for the container.

The beauty of this approach is that it will run anything that you run today, a virtual machine workload could host Exchange, Apache, DB2, etc, so it  provides a relatively simple migration path to the cloud. VMware isn’t the only vendor going down this road, Amazon’s EC2 and 3Tera’s AppLogic platform are other examples of virtual machine-based approach to cloud computing. This VM-based approach is what Drue referred to as “system infrastructure as a service” in his recent blog on defining cloud computing.

Microsoft’s Azure is a bird of a different color and fits Drue’s definition of “platform as a service”. The hardware in the data center of an Azure cloud will look much the same as what you would see in a cloud data center running VDC-OS, the difference is in the software layer, and how applications are built. The software layer for Azure (hopefully they’ll be more details of this later) consists of two pieces:

• Microsoft Azure operating system: This part is responsible for managing all the hardware (servers, storage, networks etc) and creating highly flexible and efficient compute infrastructure. For the record, Microsoft seems to be in two minds about what to call this layer, in their keynote (which Drue covered here) they were very keen not to call this layer an operating system for fear of confusing people about the nature of the platform. Unfortunately, in a presentation they gave to analysts, they described Azure as "An Internet scale cloud services platform hosted in Microsoft data centers, which provides an operating system (my emphasis) and set of developer services that can be used individually or together"
• Microsoft Azure Platform Services: These are relatively high levels services including database, identity management, .NET execution environment, SharePoint document management etc.

Workloads in this cloud will be built using .NET, and will leverage the various platform services to build an application. As such those applications if written correctly will run on standalone Windows servers or in the Azure cloud, so there is no virtual machine in the server virtualization sense. Instead each .NET application running in the cloud will be running in a virtual environment that prevents unplanned interactions between different applications.

Perhaps the best way to understand the difference is to look at an example. Let’s say we want to offer word processing as a cloud application on both platforms. For VDC-OS we could leverage an existing application such OpenOffice and use a virtual desktop approach where each user gets a copy of the word processor along with a minimal operating system (perhaps a stripped down LINUX) running inside a virtual machine. For Azure, the word processor would have to be written as a .NET application from scratch, making use of the Azure Platform Services to handle such things as storing data, ensuring access control and privacy etc. The user interface would be a web browser, and each new user would have a separate instance of the .NET application running in the cloud.

If you’ve been following the “cloud”, then the Microsoft model should sound familiar, it is very similar to Google’s cloud which also offers an application programming interface and key services such as databases. The unanswered question at this point is whether Microsoft’s Azure (which is aimed exclusively at Google) is the only weapon in their armory or will they also announce a platform built around a future version of HyperV to compete with VMware’s VDC-OS? My bet is that they will “drop the other shoe” in 2009 and announce VDC-OS type platform. Stay tuned to see if I’m right!

Posted by: Nik Simpson

This week, Microsoft announced it???s cloud platform Windows Azure and one thing is for sure, it looks nothing like VMware???s Virtual Data Center OS initiative (VDC-OS) announced at last month???s VMworld conference (for reference, see Chris Wolf???s Keynote Blog). The... Nik Simpson

Today Microsoft announced Windows Azure, their entry into the cloud computing space.

Right now there aren't many details, but it appears Windows Azure is more of an cloud initiative that encompasses several parts including:

• IT infrastructure offered as a service (compute, storage, virtualization)
• Development environment that enables their vast development community to develop distributed applications designed for the cloud (.NET Services)
• Hosted on Microsoft's data center network

Microsoft's message is somewhat similar to VMware's message last September at VMworld. At VMworld, VMware announced their Virtual Data Center Operating System (VDC-OS). VDC-OS isn't an operating system per se, it's more of an initiative to own the server virtualization ecosystem. In that same vein, Windows Azure isn't an operating system in the strictest sense. It's more of an initiative.

What Microsoft is doing is playing to their strength. They are enabling their huge developer community to develop applications for the cloud infrastructure they are hosting within Microsoft's data center network. If you're a developer of a windows application, you certainly want your application to run on Windows Azure. It's almost a no-brainer. It's the same reason developers ported their applications to Windows years ago. Microsoft also plans to customize the experience for mobile, desktop, laptop, etc. Making Azure a client platform play too. Key for them, own the experience and own the customer platform.

On the other hand, Microsoft's strength may hurt in other ways. First, they are hosting Windows Azure within their own data center. This means that Microsoft joins the ranks of Google as a SaaS provider rather than a pure infrastructure play, like VMware's vCloud network. One of Google's perceived weaknesses is the ability to port applications to their cloud. Microsoft is clearly attempting to compete with Google's app engine here. So, to be clear, this isn't a direct move toward competing with VMware from an application development sense.

But, by hosting Azure in the own data center, they will also have to compete with the vast network of other cloud providers out there that are enabled by VMware's vCloud, Amazon's EC2, and Citrix's C3. These clouds are OS agnostic. Customer's may feel more affinity toward them so that they can move their workloads between cloud providers without lock-in. Second, Microsoft is now bearing the cost burden of hosting applications on Azure by building their own data centers. I wonder how well this model scales over time. If Azure takes off, can they build enough space to host all of the applications developers want to host and customers want to use. If Azure doesn't take off, then a big investment in Microsoft data centers is lost. Finally, what about competition. Microsoft competes with developers in the software space. Will Microsoft allow WordPerfect, LotusNotes, GroupWise, or any other software competitor to run on their cloud? Would a competitor want to run on their cloud? It raises the question of whether brand is important to customers for horizontal applications hosted in the cloud as a service (like email). Do customer care that their email service on their mobile phone is exchange or something else?

Should be interesting to watch. Stay tuned.

[posted by: Drue Reeves]