collective unconscious of the smarter planet

Forget workload optimization for big data. Microsoft makes a case for using arrays of cheap, commodity x86 servers to run big data analytics.

Infrastructure vendors’ vision of big data rigs based on scale-out NAS won’t come to fruition, according to the Microsoft executive heading the company’s big data push for SQL Server 2012.

David Campbell, a Microsoft Technical Fellow in the Data & Storage Platform Group claims personal responsibility for Microsoft’s adoption of Hadoop as both an app on the Windows platform and Azure. In conversation with The Register he declared himself “Diametrically opposed” to big data rigs built on scale-out storage. To explain his reason he challenged your correspondent to “Do a census of big data implementations. Ask how many are built on off-the-shelf products and how many are built on scale-out storage.”

All the examples Campbell could list were built on commodity hardware. “The evidence is there if you look,” he said, asserting that the market has already decided that a RAIS – redundant array of independent servers – approach typified by the way containerised data centres operate is superior to the somewhat exotic hardware involved in scale-out NAS or dedicated analytical appliances.

“I used to think the big online players were outliers,” he added. Now he thinks they got the approach to big data right the first time.

Campbell is also cool on the role of the data scientist, analytical experts who blend hard-core data-crunching skills with an understanding of moving bits at scale and can then translate their efforts into business insights. Such workers are in very short supply, he says, and industry cannot assume that the crop currently taking up the first university courses in the discipline will reach the workplace in the next five years.

Microsoft has therefore tooled SQL Server 2012 so it can satisfy a data scientist’s darkest big data desires, then pass the results of their efforts to lesser folk in IT and around the business.

“People ask me if they need to hire a data scientist,” Campbell asked a Microsoft event in Sydney today. “I say that if they can connect their people to the output a data scientist creates, maybe not all the work needs to be done in-house.” To help things along, SQL Server 2012 therefore includes Power View, a new data visualisation too which makes it easy - with the help of Excel - to turn data into something the average executive can understand.

Campbell is also optimistic that, over time, more suit-wearing types will be happy to drive tools like Power View, as “milennials” fluent in Excel syntax enter the workforce and start to crunch their own data.

An interesting article on Dell’s bespoke server unit which targets the world’s 20 largest hyperscale data center operators. Facebook was an early success story before they founded the Open Compute project and started designing their own servers, like Google before them. But now Dell is looking to commercialize some of the designs they originally developed for this space.

It has been five years since Forrest Norrod and his colleagues at Dell drew up the first custom server design on a napkin at a bar at the Driskill Hotel in Austin, Texas, getting the server maker into the tailoring business. Dell now custom fits servers for very precise workloads and can cater to the tight data center power and cooling requirements found at hyperscale web operators.

The tailoring unit, called Data Center Solutions (DCS), has now grown to over $1bn in sales, says Norrod. Norrod was vice president and general manager of the unit when Dell first started publicly talking about its operations back in October 2008. He is now general manager of server platforms at Dell, and tells El Reg that the DCS business is now a “greater than $1bn a year business,” adding: “We beat that a while ago.”

DCS was founded originally to chase the world’s top 20 hyperscale data center operators, and creates stripped-down, super-dense, and energy-efficient machines that can mean the different between a profit and a loss for those data center operators. These DCS machines were not aimed at general purpose server users, whose workloads generally run on one machine and who need RAID disk controllers, service processors, and other high availability features because all of their eggs are in one basket (if not literally, then there is one server per workload – so it amounts to the same if you are looking at it at the app level). The DCS custom designs were built for companies running parallel workloads that have redundancy, data replication, and failover built into the software stack – so a regular PowerEdge server would not just be overkill, it would be plain stupid.

Facebook was the poster child for the DCS business before the social media giant decided to launch the Open Compute project last April, open-sourcing its own server and data center designs and going straight to original design manufacturers (ODMs) to build its gear.

Dell struck oil with this custom server thing, but Google builds its own gear, and now so does Facebook. Even fellow Texan Rackspace Hosting is using whitebox servers to get more server for the dollar.

But a year before this all happened, Dell saw the writing on the bespoke server wall and did a smart thing: it partially commercialized some of the DCS designs and took them to market as the PowerEdge-C machines. But you can’t just log into the Dell site and buy a PowerEdge-C machine, you have to engage in a formal sales process so Dell can make sure you get the right iron.

“Our aim with the PowerEdge-Cs was for the next 1,000 customers who needed DCS-style machines, and we have blown way beyond that,” brags Steve Cumings, executive director of marketing for the DCS unit. And while Cumings won’t talk specific numbers, he adds “it is not 1,001, either”.

In the Dell lingo, the custom machines are known as the DCS “classic” boxes while the other cloudy boxes are called “PECs” after the abbreviation of their formal name. The PowerEdge-C machines not only traditional multi-node bare-bones servers in 1U and 2U chassis as well as a 3U chassis that can cram up to a dozen single-socket microservers into a 3U chassis. Dell has even built mini-servers based on VIA Technologies’ X86 processors for hosting customers looking for cheap, dedicated nodes. In all cases, these servers have shared power and fans and precious little else but CPUs, memory, and disks.

The DCS unit has another part of the business, which is the modular data centers built from the shipping container or from other modular components. Microsoft is a big Dell customer for modular data centers. Cumings says these containerized data centers are only available to the top-end hyperscale customers because there is so much demand that Dell can’t meet it. Of course, demand is a relative thing. Cumings estimates that worldwide, there are on the order of several hundred containers being used as data centers among the hyperscale crowd. “Our impression is that we are comfortably number one in that market,” says Cumings.

Whether containerized data centers can go quasi-volume, as the PowerEdge-C servers did with several of the DCS custom server designs, remains to be seen. A lot depends on how radically customers are prepared to change their data center operations, how outdated their glass houses are, and how quickly they need to upgrade.

Dell has not broken out shipments and revenues for the DCS unit in the past, but it has hinted that this stealthy part of its business would have been among the top five server shippers in 2008 – and that in some quarters would have ranked as high as number three. This ranking would also depend on the shipments for Dell’s other stealth server business, its OEM Solutions Group, which OEMs Dell’s traditional PowerEdge servers for appliances, kiosks, and other interested parties. Three years ago, the OEM Server Group was twice as large, in terms of revenues, as the DCS unit. The gap has probably closed significantly since then.

Back in October 2008, the DCS unit had 200 employees, mostly engineers and sales people who helped craft machines and the houses they run in for hyperscale customers. Three-and-a-half years later, DCS now has 400 employees. Both then and now, DCS relied on other parts of Dell for back office functions, parts acquisitions, and manufacturing. Norrod says that while DCS uses the same manufacturing facilities as the general-purpose PowerEdge machines, they tend to have dedicated lines because the DCS run is usually 10,000 or more of the same thing, rather than a handful of similar machines built on demand for one set of customer orders that day, followed by a complete new set of machines with different configurations once they are built. You have to tool and run a DCS line differently from a PowerEdge line, he says – and in some ways, it is easier.

If the employee count is any guide, then it looks like the DCS biz has at least doubled in that time and is probably about the same size as the Dell OEM Solutions Group. Dell had about $8.2bn in servers and networking revenues in the trailing four quarters, and it is not unreasonable that these two stealthy server units could account for around a third of Dell’s server revenues.

In the latest server number out of IDC, which covered the fourth quarter of 2011, density-optimized servers like those sold by the DCS unit accounted for 132,876 units (up 51.5 per cent) and generated $458m (up 33.8 per cent). Dell had 39 per cent share of shipments of these boxes (that’s 51,821 machines) and 45.2 per cent share of sales (or $195m). IDC says that this was double the revenue and shipments of the nearest competitor in this category. Clearly, IDC’s definition of a density optimized machine and DCS’ sales SKUs don’t overlap completely for DCS to be pushing more than $1bn in sales per year. But Dell wanted to brag about the IDC numbers just the same.

ARMed … and possibly Tilera’d and FPGA’d

Dell Enterprise Products Group, which makes the PowerEdge line, has been monkeying around with ARM-based servers for years now, and Cumings says that the DCS engineers took another stab at it with the latest rev of ARM chips from unnamed suppliers in the past year – just to keep up to speed on what is possible with these ARM chips in terms of performance and thermals.

“If we see a market develop, we are ready to go,” says Cumings. “We have done a good job in seeing potential markets coming. But we are not shipping a product now and I can’t tell you when we might.”

The DCS engineers have done some research on many-core processors from Tilera, but Cumings concedes that Dell has “spent less time looking at this”.

That said, when it comes to the DCS classic designs, Cumings says that Dell will “look at any technology that will solve a customer’s problem”.

That could mean field programmable gate arrays, GPU coprocessors, and all kinds of weird stuff someday. (That’s El Reg speculating, not Dell DCS talking.)

For now, the DCS unit is focused on five key markets: hyperscale web, big data, cloud, hosting, and high performance computing. The latest projections from IDC show CPU shipments in the cloud segment to be growing at a compound annual growth rate of 15 percent between 2012 and 2015, with HPC growing 7.3 per cent compared to shrinkage of 1.2 per cent in the traditional, general purpose server space. Cumings says that Dell’s DCS business in the five key growth areas is larger than the sub-markets at large, and won’t be specific about how much larger because this is a competitive advantage for Dell.

“The growth is significant enough that DCS was created with its own resources to chase the opportunity,” says Cumings. “Dell believes in this business and it continues to grow.”

This means we won’t hear about any defections from Facebook or any other name-brand hyperscale customers who don’t talk about where they get their servers.

Not only are Oracle hardware sales and revenues declining, Oracle is also slowly killing off its reseller channel.

The road ahead for Oracle’s plucky band of hardware resellers in not certain say analysts.

The admonition comes in the wake of Oracle’s latest numbers which show that software licensing and support revenues rose in its third quarter but hardware and systems support fell 16 per cent and and four per cent respectively.

Commenting on the numbers, Canalys boss Steve Brazier, said the extent to which Oracle had “shrunk” the Sun server biz since the acquisition is “quite astonishing” and the reason is that “they don’t understand the channel”.

“They [Oracle] put direct people from the software business in charge of hardware channels. Its clearly not working, the business is sinking quickly,” he said.

Brazier added there was “no sign” of Oracle recognising and reversing this trend and claimed the boil first began festering on the day Oracle completed the acquisition of Sun when Larry Ellison said it was taking dealer accounts direct.

“It hasn’t gone well since then. The rest of Oracle’s business, the Right Now acquisition, is doing very well as a software company as it has always done but the hardware business is in crisis and will be difficult to turn around,” he added.

Oracle has posted year-on-year declines in sales and revenues for seven of the eight quarters since it acquired Sun Microsystems, according to abacus stroker IDC.

Nathaniel Martinez, programme director for server research EMEA at IDC, told The Reg that resellers were being marginalised by Oracle and the direction of the company suggested it will “pull out of the hardware channel”.

He said it may keep some larger systems sellers at the very high-end of the market but the “volume side is a dead end”.

Mike Norris, chief executive at Computacenter, said the only reason Oracle would completely dismantle the hardware channel was if its pulled out of system space but some strategic thinking was required to fire up systems sales.

“To be successful in hardware Oracle needs to engage with the channel more effectively and sort out the direct issues,” he said.

Oracle did not respond to calls for comment.

Another good run-down of the HP ProLiant Gen8 - this time from Forrester. They seem to believe this is a pretty significant announcement.

On Monday, February 13, HP announced its next turn of the great wheel for servers with the announcement of its Gen8 family of servers. Interestingly, since the announcement was ahead of Intel’s official announcement of the supporting E5 server CPUs, HP had absolutely nothing to say about the CPUs or performance of these systems. But even if the CPU information had been available, it would have been a sideshow to the main thrust of the Gen8 launch — improving the overall TCO (particularly Opex) of servers by making them more automated, more manageable, and easier to remediate when there is a problem, along with enhancements to storage, data center infrastructure management (DCIM) capabilities, and a fundamental change in the way that services and support are delivered.

With a little more granularity, the major components of the Gen8 server technology announcement included:

• Onboard Automation – A suite of capabilities and tools that provide improved agentless local intelligence to allow quicker and lower labor cost provisioning, including faster boot cycles, “one click” firmware updates of single or multiple systems, intelligent and greatly improved boot-time diagnostics, and run-time diagnostics. This is apparently implemented by more powerful onboard management controllers and pre-provisioning a lot of software on built-in flash memory, which is used by the onboard controller. HP claims that the combination of these tools can increase operator productivity by up to 65%. One of the eye-catching features is an iPhone app that will scan a code printed on the server and go back through the Insight Management Environment stack and trigger the appropriate script to provision the server.[i]Possibly a bit of a gimmick, but a cool-looking one.
• Smart Storage – More of a roadmap than a single product, Smart Storage starts with the introduction of Advanced Data Mirroring, a triple-redundant striping technology that provides a claimed 1000X (I have no way to verify this number, but logic says that three stripes will be much more reliable than two by a large margin if you replace the failed disk promptly). Also announced were intelligent flash caching for improved performance and a combination of faster memory and PCIe 3 I/O.[ii]
• Location-Aware Infrastructure Technology – Introduced under the rather opaque term “3D Sea of Sensors” (the sensors are not particularly 3D and there is no obvious “sea”), HP has introduced some extremely powerful infrastructure management capabilities that provide immediate benefit and can also work as part of a comprehensive DCIM solution. The constituent parts included location-aware racks and servers, intelligent PDUs, and rack-level power capping. Combined with other unspecified tools, these are the core capabilities to implement comprehensive intelligent power and cooling management, visualization, and workload-aware scheduling. Note that in order to fully utilize these capabilities you have to buy into a complete HP infrastructure stack of racks, and PDUs and their associated software, as well as the servers themselves. Looking into my crystal ball, it’s pretty obvious that HP has serious designs on the DCIM space, and current vendors with whom it is in “co-opetition” should be looking over their shoulders.
• Insight Online – This was in many ways the most significant piece part of the announcement, comprising as it does a complete online portal for the delivery (“cloud-based” of course as is everything from Kleenex[iii]to tractor parts) of diagnostic, maintenance, and other services to HP customers. These services include reactive diagnostic and remediation as well as an escalating menu of proactive services and additional operational assistance, and the portal serves as a central integrator of all information about a given asset, including lifecycle and contractual details as well as technical information. HP makes claims that this facility will reduce time to problem resolution by up to two-thirds and improve first-call resolution rates. Obviously it is impossible to judge the real operational quality of a complex service like this from a presentation and staged demo, but on the face of it, HP has really moved the needle in terms of service delivery with this capability.

My net take is that this is a significantly more important announcement than the last several from HP or any other mainstream server vendor, and it sets a high bar for competitors. In the coming month or two we can expect other competitive announcements, and I think that some pieces of hardware, such as PCIe-3, improved memory reliability and performance, and increased integration of flash memory into storage, will be replicated wholly or in part by competitors. What will probably set HP apart is the cumulative impact of their intelligent provisioning, diagnostics and update capabilities, along with the potentials of their service portal and associated services.

For HP customers this is unmitigated good news. For competitors it is a challenge, and we anxiously await their responses. Any HP customers are welcome to weigh in on their impressions of these announcements.

A detailed run-down of HP’s new ProLiant Gen8 servers.

Look out system administrators: Hewlett-Packard wants to give you more time to play video games or polish up your resumes – or both – with the forthcoming launch of its ProLiant Gen8 servers. .

As part of its annual shindig with partners and resellers, which was hosted in Las Vegas a week ago, the biggest server shipper in the world previewed its next generation of ProLiant x86 servers. The Gen8 machines will be based on the also impending “Sandy Bridge-EP” Xeon E5 processors from Intel, which are due for their own launch before March comes to an end. Because these Xeon E5 chips are not out yet, HP was limited in talking about the feeds and speeds of the Gen8 machines, and as El Reg previously reported, the company’s top server brass talked generally about the improved I/O and storage scalability of the boxes and how this was critical in data centers where storage capacity needs are far outpacing the need for more CPU capacity. We glossed over the management capabilities HP talked about in our initial story, and now we will drill down into it.

During the webcast previewing the Gen8 boxes, Mark Potter, general manager of the Industry Standard Servers and Software division at HP, explained that HP set out to re-architect its machines, systems management tools, and back-end support systems as part of the “Project Voyager” initiative, a two-year, $300m effort by the company to revamp its server businesses. (The companion projects in this $300m effort are Project Moonshot, the low-energy server effort that HP announced back in early November with ARM-based servers. Project Odyssey, also debuted last November and will bring the Xeon processors from Intel to the Integrity and Superdome 2 classes of Itanium-based machines and make Linux and Windows more like HP-UX in terms of scalability and reliability for mission-critical workloads.)

“This is about re-architecting the server so it is ready for the scale that the cloud needs,” said Potter, saying that the current way of doing manual operations on servers was “unsustainable.” He said that in a typical data center, weighing in at 10,000 ft², manual operations cost an average of $24m over three years, and that running the facilities manually (rather than automatically) adds another $29m in higher energy costs over the same three years. He cited statistics that this class of data center typically has a downtime cost of around $10m an hour.

With the system management tools that HP is rolling out with the ProLiant Gen8 boxes, the tools would give back another 30 days a year (that’s six weeks if you work a five-day week) per system administrator and would also allow companies to double the capacity in their data centers because of easier and more automated management and more sophisticated power capping and load balancing across machines in the data center.

“These servers are so smart that they are going to virtually take care of themselves,” said Potter. That may not be music to the ears of system administrators, but it probably is to the beancounters. (Right up to the moment where something really awful goes wrong and no one on staff has any idea how to fix it because the CEO used the sysadmin budget to buy a corporate jet.)

The system software that HP has cooked up is agentless, and the system now boots up in under three seconds. The servers have over 1,600 parameters that are tracked inside the box through what HP calls Active Health, which not only allows for problems to be resolved around five times faster than with the predecessor ProLiant Gen7 machines, but also allows for Insight management tools to work with HP’s support systems (now branded Insight Remote) to do proactive fixes before something goes wrong. So if a disk drive is getting wobbly, the system notifies HP, which ships a new drive. Simple stuff like that. The ProLiant G6 servers from several years ago had a “sea of sensors” that were dedicated to monitoring power and cooling to try to optimize the servers for power efficiency. But with the Gen8 machines, the idea is to focus on the health of the system.

“We have richer information, and we can get at it five times faster,” John Gromala, director of marketing for the ISSS division at HP, tells El Reg. “And that information can flow back to HP to help the company to improve its support operations.”

In early tests, the new Insight Online and Insight Remote services working through all those new sensors helped system administrators attain a 95 per cent first-time fix rate on problems and fix problems 40 per cent faster, too.

The new ProLiant Gen8 tools also include Smart Update, which allows the provisioning and updating of thousands of servers with the click of a mouse. On a single server, Smart Update runs on the Integrated Lights Out (iLO) service processor in the box, but if you are managing a large number of machines, you plunk it onto a Windows or Linux machine and it can then sequence updates across hundreds or thousands of machines, both for updating the firmware on the ProLiant machines and any drivers that are running to link peripherals to the server.

“This is the single biggest thing that IT shops have to deal with,” says Gromala.

Potter, his boss, said that on a rack of 32 PowerEdge servers from Dell, it took 295 minutes to provision the machines, but with the Gen8 machines and Smart Update tools, 32 machines could be provisioned in 10 minutes. Presumably the ProLiant G6 and G7 machines were no more or less pokie than the PowerEdgies.

Smart Update does not provision and patch hypervisors, operating systems, or application software. It does link into the new HP tech support portal, called Insight Online.

Stack ‘em and rack ‘em

HP is thinking more than across a bunch of servers in a rack, but across all the racks in the data center. In conjunction with the ProLiant Gen8 preview, HP trotted out Location Discovery Services and Thermal Discovery Services, two bits of software from HP’s Technology Services unit, which worked in conjunction with the ProLiant server group to cook up these extensions to the Insight Control v7 management tools. These Insight tools are one of the reasons why HP needed to buy Compaq a decade ago.

The ProLiant Gen8 machines will come with Platinum Plus-rated power supplies, which have a 94 per cent efficiency rating. But this is not enough to make the data center itself more power efficient. The location and thermal discovery services will allow a server to figure out where it is in the data center racks and rows, what power distribution units it is feeding off of, and what the thermal and power conditions are like around it. Then, having assessed its thermal and power environment, the server can use data from these tools to automatically configure its power capping settings so it doesn’t cause an overheating situation. All of this data is automatically captured by the PDUs – yup, you need to buy HP PDUs – and sysadmins don’t have to try to keep their server power cap and location data in a spreadsheet.

What HP did not talk about during its preview is what all of the add-ons for its Insight Control v7 software, as well as Insight Online, would cost IT shops. One thing for sure: You can bet it will not be free.

The latest quarterly report from HP reveals continuing issues… no surprise…

Five months into the role as HP CEO, Meg Whitman is finally detailing the tech titan’s turnaround plan that involves “fixing execution” and cutting costs to save cash before it ups investments in R&D.

In a tough fiscal first quarter, HP ironically saw an upturn in the software and to a much lesser extent the services businesses – the strategic areas of focus for Whitman’s hapless predecessor – but declining sales across all core hardware divisions again.

Sales in the three months ended 31 January fell 7 per cent to $30bn, while operating and net profits sank 41 per cent and 44 per cent to $2bn and 1.46bn respectively.

“Frankly, it was a tough quarter, and every business had its challenges,” said Whitman in a call with analysts last night.

…

Enterprise Servers, Storage and Networking (ESSN) revenues declined 10 per cent to $5bn: networking revenues were flat; Industry Standard Servers fell 11 per cent, Business Critical Servers dropped 27 per cent and storage was down 6 per cent.

Whitman described this segment as a “highly competitive environment that was compounded by the hard disk shortage. in our broader storage business, we’re still working through a product transition”.

So that leaves Software and Services, the units that were a core part of Apotheker’s vision which were thrust into the foreground as he mulled over options for the future of the PC biz, killed of WebOS hardware and splashed the cash on Autonomy.

Services revenues hardly provided reasons for investors to cheer - sales grew one per cent to $8.5bn, with Technology Services turnover up 2 per cent, Application and Business Services flat and IT Outsourcing grew 2 per cent.

The Software division pushed up revenues by 30 per cent to $946m including numbers from Autonomy, fuelled by 12 per cent growth in licensing, 2 per cent growth in support sales and 108 per cent in services.

Whitman has been on a tour of duty since the own goals HP scored last summer, attending 80 customer visits in the US and Europe and meeting staff and channel partners.

“We’ve been working hard to set the right tone, calm the waters and reassure our stakeholders that HP is the same reliable company … So what have I found? Certainly, I found some skepticism. But I have also found that we have incredible support.”

She said HP is on the right trajectory “but we have a long road ahead of us” and its recovery plans are not helped by continued cautious spending in US commercial, weak demand in consumer and the challenges in Europe.

Whitman said the major issues to overcome include “fixing our execution” by reducing SKUs to remove supply chain complexities; upgrading sales tools and systems to react more quickly to punters; and upping sales productivity by “rationalising our go-to-market”.

The second major hurdle has roots in the strategy devised by disgraced former CEO Mark Hurd, who slashed R&D. HP said its businesses were under “intense competitive pressure” and that it was feeling the strain from “tectonic [industry] shifts”.

“We didn’t make the investments we should have [made] during the past few years to stay ahead of customer expectations and market trends. As a result, we see eroding revenue and profits today. We need to invest now as a market leader from a position of strength.”

The final issue pulled up by Whitman is how HP reacts to emerging “delivery, consumption and business model[s]” for tech areas including cloud, security and information management.

Whitman said there was a “once-in-a-generation” chance to define the future of tech – clearly she can still draw upon cliches learned in her brief political career – but she said HP needs to “stabilise financial performance” and generate profits to invest.

“And it’s clear, from both our revenue and margin profile, that our current cost base just isn’t affordable. On the current trajectory, we just won’t have the capacity that we need to invest,” she said.

“For years, we’ve been basically running our business in silos. And under that model, we built some of the leading franchises in technology, but it’s also made us too complex and too slow,” she said.

HP has been through years of pain with a series of redundancy programmes hitting morale, but more can be done to “streamline operations” such as tackling business processes by standardising and automating workloads.

“We can also take a ton of complexity out of the system, improve our effectiveness and significantly reduce costs,” said Whitman.

“It’s not easy work and it’s not a quick fix, but it holds the potential to improve the way we operate and execute, and it simply has to be done. We have got to save to invest. We have got to save to grow … I have no doubt that we’ll turn HP around.”

Turnaround strategies take time to bed in but with the founders’ families and an incredibly political board to contend with, Whitman will be looking over her shoulder for some time yet.

OpenStack has opened up a temporary cloud, called TryStack, to try and entice developers away from Amazon.

How does a cloud project solve a problem like Amazon? The once genteel etailer of toasters, books and CDs has now become a byword for “cloud”.

People just can’t stop stuffing more of their data into Amazon’s EC2 service. The number of objects held in EC2’s S3 storage service grew by nearly 200 per cent in 2011 to 762 billion, compared to 156 per cent growth in the year before.

More will be mopped up more in 2012, as Amazon has made it easier and even cheaper to use S3.

Bezos’s company cut its entry-level prices by 10 per cent from 1 Feb, to $0.125 for the first terabyte. In January it uncloaked the AWS Storage Gateway beta to act as a cloud-based data back-up service for companies, thereby hovering in even more.

Developers are the problem. Amazon has made it easy to test and develop apps at a very low price using open or at least familiar programming languages, tools and databases. The service couldn’t be more ubiquitous: fire up a browser and it’s easy to find and start EC2.

If you’re the OpenStack Project hoping to challenge Amazon for the business customers putting their apps in the cloud, then one approach might be to tempt developers with a suck-it-and-see scheme for this “Linux for the cloud” effort.

OpenStack is about to open up FreeCloud, which lets you test the idea of OpenStack while running it hosted in a sandboxed environment. FreeCloud’s also getting the re-branding iron run over its hyde: it’s now called TryStack. The idea is TryStack lets you test OpenStack without either having to download and install the code on your own servers or – if that sounds like to much hassle – have to sign a contract with a service provider running OpenStack in their cloud before you know you’ll like or need it. It’s meant to tie into the Devstack Openstack development toolkit here.

With Amazon, there’s no code or modules to download – the service is ready to go reducing the barriers to experimentation and producing potential future customers.

Jonathan Bryce, OpenStack project chairman and chief technology officer and founder of The Rackspace Cloud, told The Reg: “We heard from several people the are interested in using OpenStack, but don’t have the sysadmins do build the KVM or networking.

“Because it’s a set of services and servers you have to set up and run yourself, and if you are developer working on an application you are more used to having access to a running environment and putting code in rather than having to build that environment.

“One of the first targets that brought this need to our attention was app developers who write tools for managing clouds - companies like Cyberduck and EC2 Firefox extension. They need a functioning version of an OpenStack cloud that they can program against. To get that they’d have to install OpenStack somewhere and to that they’d need the hardware.

TryStack has been in use by about 12 customers for the last five months as FreeCloud. It was built by Rackspace and NTT using Dell servers and hosting and bandwidth from Equinox - all OpenStack Project members. TryStack runs the last release of OpenStack, called Diablo, coming with compute, object storage and Glance for doing snap shots, with dashboard and authentication.

You’d think TryStack would use stealth to attract and retain developers, but it doesn’t and TryStack is purely a developer service that’s not been built for long-term hosting. Not yet, at least.

TryStack users must buy into an invented currency, called Stack Dollars. Everybody gets 100,000 Stack Dollars that gives them “a couple of gigabytes for a couple of days”. Stack Dollars don’t have any actual monetary value, and they can be topped up. The smaller your compute instances the longer the dollars last, the larger the quicker they burn. Once your finished, your compute resources return to the pool while TryStack doesn’t come with any SLAs and the service might get taken offline for upgrades Bryce said.

The OpenStackers behind TryStack really don’t want you getting any ideas about hanging around. For OpenStack, however, this might be the best way to grow against Amazon. The problem is commercial operations like Dell, Rackspace, Citrix and Hewlett-Packard are either delivering or building clouds using OpenStack and so wouldn’t appreciate the free competition.

Rackspace, Bryce’s employer, was a instrumental in creating OpenStack and has led construction of significant portions of the code – compute and storage – that it’s now deploying on its hosting servers. Rackspace just notched up its first billion-dollar year after 12 years in the biz.

HP’s OpenStack cloud has been in beta since September – it’s currently an Infrastructure-as-a-Service service providing compute and storage. With Citrix’s CloudStack, you download either uncompiled or compiled binaries. How Citrix charges isn’t clear and it still seems to relying on the Cloud.com start-up it bought last year for users to configure the code. Dell’s not getting its hands dirty, and is now selling an OpenStack “solution” – blueprints and advice on setting up an OpenStack cloud running on Dell servers.

The thinking behind TryStack is that it will pique developers’ interest in a cloud architecture for everybody who’s not Amazon – PC and server manufacturers, service providers, software makers and others. “It’s about making it easy for people to try it out … hopefully that leads to business for all the OpenStack companies afterwards,” Bryce said.

But translating that into a paying business for those with a stake in the project will be another thing altogether. With the “deploy” portion of the development cycle not available and with so many OpenStack clouds in different states of public availability, it’s likely Amazon will continue to grow fat, and fast, before OpenStack starts racking up.

EMC shook things up a bit last week when they introduced a new, very smart flash storage solution - VFCache. It caches “hot” data (important information that is needed again and again) from a storage array so that servers can access it extremely quickly and efficiently - until its not needed.

The perfect server flash storm hitting storage arrays has generated EMC’s well-signalled Lightning strike; VFCache has arrived, extending FAST technology from the array to the server. Project Thunder is following close behind, promising an EMC server-networked flash array.

This is a major announcement and we are covering it in depth.

FAST (Fully-Automated Storage Tiering] moves data in an EMC array into higher-speed storage tiers when it is being accessed repeatedly and server applications don’t want to wait for slow disks to find their data.

EMC boasts that its customers have purchased 1.3EB of fast-enabled since January 2010, and it has shipped more than 24PB of flash drive capacity, more than any other storage vendor. Times have changed and flash in the array is no longer enough.

Fusion-io has attacked the slow I/O problem by building server PCIe bus-connected flash memory cards holding 10TB or more of NAND flash, and giving applications microsecond-class access to random data instead of the milliseconds needed from a networked array. The threat here is that primary data could move from networked arrays into direct-attached server flash storage.

EMC’s response is to put hot data from its arrays into a VFCache (Virtual Flash Cache) solid state drive in VMware, Windows or RedHat Linux X86 servers from Cisco, Dell, HP and IBM. This provides random read access performance equivalent to Fusion-io once the cache has warmed up and is loaded with hot data.

VFCache is a 20-300GB PCIe-connected flash memory card, using, as rumoured, a Micron SLC card (P320h we think) or LSI WarpDrive SLC flash, Micron being the primary supplier. (Micron has just tragically lost its CEO, Steve Appleton, in a plane crash after winning what must have been a hotly-desired OEM contract.) The P320h is a fast flash card, doing 750,000 random 4K block read IOPS.

The EMC cache increases 4KB - 64KB block random read I/O speed but not write I/O speed. VFCache will not cache read I/Os larger than 64KB. There is no write caching.

We’re told “testing in an Oracle environment showed [an] up to 3X throughput improvement and 50 per cent reduction in latency.” EMC asserts that “VFCache is the fastest PCIe server Flash caching solution available today.” This does not necessarily mean it is faster than Fusion-io’s server solid state storage; that is not a “caching solution” in the way VFCache is.

Storage array and cache interoperability

EMC says VFCache works with EMC VMAX, VMAXe, VNX and VNXe array FAST. Does VFCache only work with EMC VMAX and VNX arrays? No, indeed not; VFCache is storage-agnostic and will work with all 4Gbit/s and 8Gbit/s Fibre Channel-connected block storage. No change is needed in the back-end block arrays.

We’re told that, by working in conjunction with EMC FAST on the storage array, VFCache offers coordinated caching between the server and the array. How does this work? EMC says VFCache’s caching algorithms promote the most frequently referenced data into the cache. Okay, but this isn’t co-ordinated caching between the array and the server. This is VFCache doing its own caching on the server irrespective of whatever caching the array is doing. For example, EMC doesn’t say the array will not cache data that VFCache is caching.

There appears to be no active interaction between VFCache and array FAST at all, EMC saying VFCache is transparent to storage, application, and user.

With writes, the VFCache driver writes data to the array LUN and, when that completes, write data is asynchronously written to the flash cache. It appears the back-end array is not involved in managing VFCache at all; in fact; it doesn’t even know VFCache exists.

Limitations and futures

VFCache has to be disabled and removed for vMotion to take place, it being a local resource for the virtual machine. It’s not possible to configure automatic ESX server failover if it’s being used and things like vCenter Site Recovery Manager with it or use it in a cluster that uses vMotion to balance workloads.

The VFCache card can have separated off DAS partitions for server app use but data loaded into them is not written to the back-end array. This is called split-card mode. It should only be used for temporary data, stuff that doesn’t need safeguarding by being written to the back-end array

EMC will add deduplication to VFCache later this year, increasing its effective capacity. It does not say where the deduplication will be done, with our assumption being that it will be less burdensome on the host CPU to have it carried out on the card itself.

There will be additional capacity points in the future and VFCache will be more deeply integrated with EMC’s storage management products and with the FAST architecture. This could be a hint that EMC’s storage arrays will co-ordinate more actively with VFCache.

VFCache and Fusion-io

Fusion-io has sold to early adopters in EMC’s view. It believes Fusion-io-type server DAS approaches do not protect data against a server crash or provide data sharing. By storing the server’s data in a back-end array it scan be protected via snapshots, replication, etc, and made available to other servers. Management is also easier. Mainstream server flash use won’t happen unless these data protection and management features are added.

Specifically, MC says VFCache is less of a drain on server resources than a Fusion-io flash store because because VFCache hands off flash and wear-level management to the PCIe card itself, whereas the host CPU does this for the Fusion-io product. It says Fusion-io CPU overhead could be up to 20 per cent higher than that with VFCache.

Development and Project Thunder

EMC will add deduplication technology to VFCache later this year, enabling an effective increase in capacity. Clearly this will best be carried out on the card to avoid burdening the host CPU. Whether that will be the case remains to be seen.

There will be larger capacity points for VFCache, possibly going beyond 300GB, and different form factors, adding blade environments to the current rack form factor. It will also integrate better with EMC storage management technologies, and there will be additional integration with FAST architecture. This means active co-ordination between caching by VFCache and EMC’s VMAX and VNX array FAST capabilities. We’ll be seeing:

- Enhanced VMAX/VNX array integration – hinting, tagging, pre-fetch for even greater performance
- Distributed cache coherency for active-active clustered environments
- VMAX and VNX management integration

EMC has also announced Project Thunder, a “low-latency, server networked flash appliance that is scalable, serviceable, and shareable. It is intended to “deliver I/Os measured in millions and timed in microseconds.”

This suggests it will use a fast server-appliance interconnect such as InfiniBand, which Oracle uses in its Exadata systems, or some form of PCIe I/O virtualisation. EMC confirmed this and said it will be working with its customers in a second quarter early access program to determine the interconnect to use.

It will be “optimised for high-frequency, low-latency read/write workloads” and will build upon the PCIe technology in VFCache. In effect this will provide a combination of the functionality offered by Fusion-io and Violin Memory products; the speed of directly-attached flash and the sharability of a networked flash memory array.

El Reg thinks other mainstream storage, PCIe flash storage, server/storage and flash array vendors will be forced to follow suit, giving a boost to either InfiniBand or IOV high-speed server-storage interconnect technologies, or both.

Storage flash landscape

VFCache is a fast fix to the threat - and opportunity - posed by Fusion-io and other PCIe flash caching suppliers to EMC on the one hand, and networked flash arrays such as those from Violin Memory, WhipTail and Nimbus now, and startups like Pure Storage, SolidFire and XtremIO on the other.

As with the introduction of SSDs into storage arrays, EMC is the first mainstream vendor to jump on the server PCIe flash bandwagon. We understand Dell is actively working in this area and expect HP, IBM and NetApp to follow suit together with Fujitsu and, maybe, HDS. It represents a recognition that disk drive latency is no longer acceptable for primary data access and that network latency is also becoming unacceptable.

Virtualised, multi-socket, multi-core, multi-threaded servers demand faster I/O than Ethernet and Fibre Channel networked disk drive arrays can provide. EMC has seen that there is a need for mainstream enterprise-class data centre I/O speed and flash dash is the way to get it.

A good analysis of where EMC is heading. Hint: it’s not just storage anymore.

It’s a vision thing: EMC was a storage company and is an information company, but in the next decade it looks like it will be a data centre infrastructure company.

This thought comes from a parsing of two Pat Gelsinger replies to an interview with EMC’s Mark Twomey, otherwise known as the blogger Storagezilla.

Reply number one was to the question “Between VMware, revenue leadership in Backup & Recovery from BRS and analytics from Greenplum is EMC still a storage company?” and here it is:

“Going forward EMC wants to be the most disruptive data centre infrastructure company in our industry. While today storage is our centre and our heritage, we’ve just shipped a new storage offering with VFCache and announced another with Thunder, increasingly virtualisation, security, management and analytics will complement that foundation to give us a broad data centre footprint.”

Hold this in your mind while we look at reply number two in answer to the question: “To you what does the competitive field look like?”:

“In some ways, no real change from the usual. NetApp, Hitachi, Dell, HP and so on but we do see two new areas of threat in storage. One is Huawei, the other is the bevy of Flash startups. We’ve spent time looking at them both. Beyond those we see that to be the leader in the data centre market we will be competing with bigger and broader IT players in the future.”

Huawei and Flash are the new areas of threat for EMC in storage. Huawei is a well-funded and determined Chinese storage supplier that has just bought out Huawei-Symantec, exiting the US in the process, and is, in the telecommunications area, something of a Chinese version of Cisco, and Cisco is concerned about Huawei as well.

For EMC, Huawei will be a competitor roughly analogous to HP, having servers, storage and networking and the ability to integrate them and extract synergies.

Flash is going to be the means to store primary data and get it shipped to servers faster than any other mainstream storage technology. I believe EMC thinks that flash will also become storage memory in servers and, as such, is likely to be sold primarily by server vendors. It will be software that will be a key technology here, with the ability to read and write data by applications in DRAM to data containers in storage memory (flash) without going through the host O/S’ disk-based I/O subsystem, looking to be a huge latency reduction factor.

Atomic writes

Two articles on atomic writes from the Wikibon consultancy – here and here – together with Fusion-io’s Auto-Commit Memory illustrate this line of thought.

The logical conclusion of this line of thought is that the long period of dominance in which primary data – both block and file – was stored in networked drive arrays is coming to an end. Disk drive arrays will become capacity vaults that protect and feed the flash stores. The Fibre Channel drive array mammoths are about to enter the deep freeze and primary data is going to be co-located with the servers whose apps process and generate that data.

One more jump needs to be made. The atomic write, bypassing the O/S IO subsystem idea, is between an app in a server’s DRAM and a data area in direct-attached server memory: DAS flash in other words. We’re looking forward to shareable flash arrays networked to servers by InfiniBand or some form of PCIe IO virtualisation. In that case the networked flash array can form all or part of a server’s storage memory, given that latency is low enough, and a server app’s atomic writes can be made to shared flash storage memory and not just to direct-attach storage memory.

Whichever supplier pulls this off and provides shareable storage memory arrays between servers – such that vMotion and the equivalents from other hypervisors becomes easily achievable – and also manages to hook the storage memory up to back-end disk drive arrays for data protection and wide area network data sharing, will be in a very strong position.

VMAXalytics and VMAXalogic

Back to the Gelsinger replies. First of all, this one: “To be the leader in the data centre market we will be competing with bigger and broader IT players in the future” – meaning the server-system vendors, like Oracle.

Secondly: “EMC wants to be the most disruptive data centre infrastructure company in our industry … increasingly virtualisation, security, management and analytics will complement that foundation to give us a broad data centre footprint.”

EMC cannot compete with companies like Oracle and the server-system companies like HP which are busy developing integrated stacks – let alone compete with Huawei – without developing its own integrated stack offerings. Of course it is doing this with VCE, which is really a partnership between EMC and Cisco, EMC owning 80 per cent of VMware.

Now let’s try putting EMC’s current and future lego blocks together with all this in mind. Cisco can provide the networking and servers and EMC the shared PCIe-speed capable flash arrays (Project Thunder). VMware, meanwhile, can offer the atomic write capability in flash super-charged Vblocks with VMAX, VNX or Isilon arrays for large-scale block and scale-out file and big data storage. The Oracle strategists have got to be assuming that VCE is going to bring out VMAXalytics- or VMAXalogic-type converged stack boxes to compete with their own Exalytics and Exalogic-engineered systems.

What EMC is doing is using storage as a launchpad to vault up into the same data centre supplier rankings as HP, IBM and Oracle.

What does this mean for other storage suppliers?

The worrying kind

Strategists and chief technology officers (CTO) will be concerned that this will mark a seismic shift in the data centre and that the era of the stand-alone storage supplier is coming to an end. The stand-alone storage suppliers have got to get deep into the converged stack platform business or face the same fate as mammoths and sabre tooth tigers.

Customers are going to buy storage as part of a system, like a car, and not as their own selected and integrated best-of-breed parts. Of course they might rent the system – from the cloud data centre equivalent of Hertz and Avis rent-a-car – but that doesn’t alter the basic fact.

Less paranoid CTOs and strategists will say: “Nonsense. Data centres are not like a car fleet. Enterprise customers will always go for best-of-breed because of the total cost of ownership advantages, performance and manageability advantages, etc.”

Will they? What if a flash super-charged Exalogic/Exalyics/Database appliance box is best of breed, and makes better use of its component software, server and storage resources than any bolted-together, DIY stack created by an enterprise or even a FlexPod-type consortium?

We’re in the realm of don’t know/can’t know for now, but one thing is for sure: if flash super-charged servers doing atomic writes run 10 times more virtual machines than current servers and are affordable, then customers are going to buy them. End of. And that will stimulate the end of the primary data-storing drive array as we know it.

So Mr Storage Supplier, are you going to crash the flash super-charged server party like EMC is doing, or will you sit this seismic shift out? Careful – you could be betting the future of your company.

IBM and EMC represent two different approaches to enterprise-class flash-based storage.

The approach to utilizing flash for high-performance, enterprise use cases is evolving. Compute-intensive servers have already been enlisted to enable high-performance applications like enterprise resource planning (ERP), customer relationship management (CRM), online transaction processing (OLTP) databases, and more recently virtual desktop infrastructure (VDI). But a high-performance storage architecture to match the high performance compute has not yet been decided on. Flash seems to be the core of the solution, but where to put this flash for optimal enterprise performance? Announcements this week from EMC and IBM suggest two approaches: one server-based, one array-based.

One of the original strengths of SAN-based storage arrays was that they could support high-performance transactional databases at higher capacities. To improve performance, faster and faster hard-disk drives (HDDs) were employed in the array: 7,200 rpm, 10,000 rpm, 15,000 rpm. Eventually, flash-based solid-state drives (SSDs) were introduced with the ability to provide up to a 300X increase in IOPS over HDDs. Although more expensive, the performance benefits of flash SSDs have become too compelling not to support. This week, IBM announced SSD support for its XIV enterprise storage array, joining its own DS8000 series and every major storage vendor in offering flash SSD support for their enterprise class arrays.

But using flash as a storage tier in an array does not fully utilize its potential for performance. PCIe-based flash deployed in the server can offer up to a 20X increase in IOPS over array-based flash. Fusion-io has capitalized on this market with its ioMemory platform of flash-based PCIe cards aimed at accelerating high-performance applications, databases, and VDI, independent from the storage array. And just this past week, EMC’s announcement of VFCache, its own server-based flash product (previously code-named Lightning), shows that EMC is also embracing this approach and wants a piece of this growing market.

There are some drawbacks to current server-based flash solutions. Their capacities are smaller, they do not scale well in the server, they are not cache coherent between servers, and they cannot provide the enterprise data integrity and data management capabilities that flash in a storage array can. So while some of the highest-performance use cases may be moving to flash on a server, these issues will prevent primary storage from leaving the SAN any time soon.

There are also several flash-based solutions between the primary disk array and the server that offer different tradeoffs. “All flash” arrays like those from Violin Memory and Texas Memory Systems (TMS) can provide higher performance than typical tiered flash in an array, addressing the capacity and data integrity gaps of server-based flash, but at a higher cost. “SAN proxy appliances” like GridIron’s TurboCharger offer a less-pricey, high performance, flash-based caching solution for the SAN that can easily be dropped into an existing architecture. “Server network flash appliances,” such as EMC’s code-name Thunder, promise to address the limited scalability and shareability of server-based flash while retaining its higher performance.

As flash prices decrease, capacities increase, and as data integrity, cache coherency, and scalability are addressed, flash will continue its slow march towards the application. But it is clear today that flash in the server is an optimal solution for smaller data sets and highest performance, while flash in the array should be leveraged for larger or more mission-critical data sets, and a number of solutions in between can improve performance while balancing enterprise priorities with cost.