The Big Payoff

The big payoff for driverless vehicles is with driverless trucks, not driverless cars, especially driverless "Ubers". By driverless trucks, I specifically mean long-haul trucks.

 

A typical long-haul trucker drives 10 hours a day, meaning the truck is idle the other 14. Some downtime is needed for refueling, weigh stations, etc., but it is reasonable that driverless long-haul trucks will double the productivity of human driven trucks, quite literally overnight.

There has been a shortage of people willing to work as long haul truckers, even given it pays a middle-class income without the need for excessive education or training. This has caused labor costs to rise.

There are currently over 1.5 million long-haul truckers and estimates are the need for long-haul truckers will approach 2 million in the next 5 years.

There are about 250,000 taxi and limo drivers, and they make less than long-haul truckers. Uber and Lyft have exposed there is much greater demand for car services than originally expected, and the capital-less model of ride-shares works well for that demand. The flood of ride-shares has depressed wages for both taxis and ride-shares. But more importantly, self-driving Ubers will be a capital intensive model and will have all the flexibility of a taxi, and none of the flexibility of a ride-sharing service.

The long-haul truck driver replacement market is a $100 billion addressable market, about 10 times that of the taxi driver replacement market.

Follow the money.

When Did Expertise Die?

I saw a recent Facebook post of Dr. Tom Nichol's commentary on PBS about The Death of Expertise.

For some unknown reason, Nichols blocked me on Twitter, so I cannot provide this opinion directly. That is his loss.

But Nichols accurately posits the rise of the public Internet has created the side effect of everyone thinking they individually are an expert. However, individuals believing themselves to be experts is only half of the equation. The other half is the discrediting of the true experts, and I believe that happened about a decade or more before the rise of the public Internet. There is a third point, which is the rise of the well known pseudo-expert, and in some cases the celebrity pseudo-expert, such as Jenny McCarthy in the Anti-Vaxxer movement, and Rosie O'Donnell in the 9/11 Truther movement. Celebrity pseudo-experts provide credibility to lay pseudo-experts such as the producers of the original "Loose Change" 9/11 Truther film.

But back to the second point, the discrediting of true experts, or "when expertise died".

In 1989, while in college, I had a roommate who was a journalism major. At that time, they were teaching journalism students expertise is a subject was inherently biasing, and that the opinions of an expert in a subject must be balanced with an opinion of someone who was not an expert in the subject.

He later worked on a story on management, and interviewed an expert in the subject, who happened to be a management professor I worked for as a graduate assistant. He had to then find rebuttal information not from another management professor, but from someone completely unrelated. To me, this was surreal, because I knew both the interviewer and interviewee, and had no reason to question the good intentions of either.

But later it all made sense to me. I grew up watching expert reporters: Jules Bergman, ABC's science reporter; and Irving R. Levine, NBC's economics reporter. I also noticed those expert reporters completely disappeared in the 1980s. Except for the doctors the networks use as medical correspondents and the aviation expert they bring in for airplane crashes, there are no expert reporters any more. I also remember every time in the 1980s we launched a Space Shuttle, the various national news anchors would state the Soviet Union's public statement opinion about the purpose of the mission, as if it was as valid as NASA's stated mission objectives, or as if NASA's stated mission was as invalid as the Soviet's opinion. This latter point goes straight to my original point about my what my roommate was taught: NASA is an expert on their space missions, their opinion must be balanced. Was the Soviet statement credible? Was it valid? Was it simply propaganda? It didn't matter. Was NASA's statement credible? Was it valid? Was it simply propaganda? It didn't matter. To the media, the Soviet position was just as valid as NASA's position. Propagandists at the Kremlin were just as valid as rocket scientists in Houston.

From a purely pop-culture standpoint, I think we tended to believe Jules Bergman on science issues because his name sounded similar to science fiction writer Jules Verne's. I think we believed the bespectacled and bow-tied Irving R. Levine because he fit our visual of what a college economics professor should look like. They were journalists, and not scientists or economists, and they fit a persona, but they were experts in their field as far as journalism went. They had connections, they could get a meeting with the real experts, they had developed a working expertise on their subject, and they had credibility with the public. But they are gone now, and have been for about 40 years.



So I think before we blame the general public, driven by curiosity, and enabled by the Internet (be it WebMD, Wikipedia, or "FakeNews"), we need to consider nature abhors a vacuum, and realize the television media created a vacuum when it cut out those quirky expert reporters, and promoted skepticism and outright distrust of expertise.

Everything I need to know about NetApp’s All-Flash Storage Portfolio I learned from watching College Football

Okay, silly title. I got the idea when Andy Grimes referred to NetApp’s all-flash storage portfolio as a “Triple Option”. To me, when I hear triple option, I think of the famous Wishbone triple option offense popular in college football in the 1970s and 1980s. And that got me to thinking of how NetApp’s flash portfolio had similarities to the old Wishbone offense.

The Wishbone triple-option is basically three running plays in one. The first option is the fullback dive play. This is an up the middle run with no lead blocker. It is up to the fullback to use his strength and power to make yardage. The second option is the quarterback running the ball. While most quarterbacks are not great runners, the real threat of the quarterback in running offenses is the play action pass, where a running play is faked, but the quarterback instead passes the ball. In today’s college football, while the Wishbone may have faded, option football remains popular, and many of the most exciting players are “dual-threat” quarterbacks who can both run well and pass well. But, back to the Wishbone. The third option is the halfback, an agile, quick running back who often depends more on his ability to cut, make moves, and change direction to make the play successful.

In considering this analogy, I wanted to find the right pictures or videos of Wishbone football to make the comparisons to NetApp’s flash portfolio, but found the older pictures and videos from the 1980s to not be that great. So I decided to take the three basic concepts: The powerful fullback, the dual-threat quarterback, and the agile halfback and look at more recent examples. I just happen to use examples from my alma mater, Auburn University, because I knew of a few plays that visually represent the comparisons I am about to make.

So first up is the fullback. The fullback is all about power. It is not about finesse. The fullback position is not glamorous. The fullback had to have the strength to face the defense head-on. To me, the obvious comparison in the NetApp flash portfolio is the EF-Series. The EF is all about performance: Low latency, high bandwidth, without extra bells and whistles which can slow other platforms down.

While I don’t have a good fullback example, I have a similar powerful running back demonstrating the comparison I am trying to make. Here we see Rudi Johnson on a power play break eight tackles and dragging defenders 70 yards to a touchdown from the 2000 Auburn-Wyoming game.

Rudi Johnson great 70 yard TD against Wyoming 2000

The next comparison is to the dual-threat quarterback. The dual-threat quarterback can run or pass with equal effectiveness. In NetApp’s flash portfolio, the obvious comparison is the All-Flash FAS (AFF), the only multi-protocol (SAN and NAS) all-flash storage array from a leading vendor. The multi-protocol capability of AFF (Fibre Channel, iSCSI, and FCoE SAN; NFS and SMB NAS) allows storage consolidation, and truly brings the all-flash data center to reality.

The play which best demonstrates the dual-threat quarterback’s potential is the run-pass option (RPO), where a quarterback rolls out and can either keep the ball and run with it, or pass it to a receiver if the receiver is open. Here we see Nick Marshall on an RPO play which tied the 2013 Iron Bowl with 33 seconds left in the game. The reason the play worked is Nick Marshall, a gifted runner, had already run for 99 yards including a touchdown.

2013 Iron Bowl: Marshall to Coates

That brings us to the halfback, also known as the tailback, or just the running back. For the sake of this discussion, and keeping with the original Wishbone concept, I will use the term halfback. The handful of teams who still run a variation of the Wishbone (Georgia Tech, Navy, Army, Air Force, and a few others), tend to use smaller, more agile athletes as halfbacks. These running backs usually get the ball on the outside, and leverage their agility to make the defenders miss. When I think of agility in flash storage, I think of SolidFire. Agility is a key feature of SolidFire. It scales with agility, provisions with agility, adapts with agility, and is the best storage for agile infrastructures like private clouds, especially private clouds using OpenStack. The best recent example I have seen of a running back leveraging agility to make a play is this run by Kerryon Johnson against Arkansas State.

Watch Kerryon Johnson's incredible touchdown against Arkansas State

So enough fun for now. But if you have a dedicated application needing performance acceleration, such as a performance critical database, NetApp’s EF-Series might be your tackle-breaking fullback powering through spaghetti code and getting the job completed despite the challenge. If you are looking to move to an all-flash data center and need consolidated flash storage to accelerate iSCSI MS-SQL databases and NFS VMware datastores on the same infrastructure, AFF is your dual-threat quarterback. And if you are looking to deploy a private cloud with the agility to grow with your workload, SolidFire is your agile halfback.

On Disruption

A few months ago, there was an email thread at my employer asking the question if All-Flash Storage was a “disruptive” technology. Disruptive, in the business sense, refers to Clayton Christensen’s definition of the term from his book, “The Innovators’ Dilemma”.

This, from a year ago, Christensen reviews his concept:

What Is Disruptive Innovation?

However, I think this is a narrow, and perhaps obsolete definition. He says Uber is not disruptive, because it did not originate in the low-end or new-market segments. However, while Uber did not disrupt car for hire, it did disrupt the capital model of cars for hire, and it did disrupt the medallion licensing model. Then the article also talks about how Netflix, in its original format (DVDs by mail) attacked an underserved periphery—not the low end, and not a new segment—of the market.

If we use the pure Christensen definition, All-Flash Arrays (AFAs) are not disruptive, but HyperConverged Infrastructure meets the definition. But perhaps we should look more broadly at the definition.

“The Innovator’s Dilemma” is 20 years old. It was written during the Dot-Com boom. Business books are not canonical. If they were there would never be revisions and follow-ons.

I think we need to take a wider view of disruptive technologies. Uber disrupted car for hire capital and licensing models. Driving an Uber is much less expensive than buying a taxi medallion, so the cost of entry was disrupted.

So how does that apply to AFAs? We know cost of IOPS is much lower with AFAs. We also know the costs of sizing and performance management dramatically decrease. One can argue the TCO of AFAs is lower. While AFAs did not enter at the low-end or a new-market segment, it did enter at a periphery, at a market segment (high transactional performance storage) where it offered a lower cost. AFAs disrupted a market segment of the overall frame storage market. Not the Mainframe attach segment, and not the extreme reliability segment, but at the assured high performance segment.

But here is another aspect of AFAs I am seeing—they mandate changes to a customer’s operational model. AFAs were made cost effective in part by using data reduction technologies (deduplication and compression). While there were some hard-drive based storage arrays which leveraged data reduction technologies (NetApp FAS, EMC Celerra, Sun/Oracle ZFS based arrays), these data reduction technologies were not available on high-end frame storage (EMC Symmetrix/DMX/VMAX, HDS USP/VSP, IBM ESS/DS8000). These data reduction technologies worked well for certain workloads: virtual machines benefited from deduplication, and OLTP databases benefited from compression.

This meant AFAs with built-in data reduction, targeting small, peripheral workloads (VDI, high-transaction OLTP), were set up for easy success.

However, at the same time other trends were occurring. To more effectively leverage the expensive high-end frame storage, some DBAs were turning on compression within their database software. Yes, this increased the number of CPUs needed to run the database, and increased their cost, but often DB licensing was a sunk cost. It was also possible to compress at the OS/filesystem level. It was not unusual in organizations where IT departments charged back storage capacity to users, for users to turn on compression in their servers to reduce their chargeback.

The second thing that happened over the last five years has been the fear of a data breach. This has driven the need to encrypt data at rest. While storage arrays offer this capability through Self-Encrypting Drives, encryption boards, or software encryption running on the array’s controller, often enabling storage encryption could only be done after upgrading the storage array to a new model. As a result, turning on encryption at the application level (i.e., the database), at the OS level (encrypting file systems), or at the VM level (using products like HyTrust) was a much faster path to security for many customers. Also, customers were assured only host level encryption ensured data was encrypted “over the wire” in addition to at rest.

The result of either of these technologies is it eliminates ability of the data reduction technology in the storage array to provide any benefit, and it returns the cost per gigabyte of flash storage to what it was with early generation, non-efficient architectures, which ultimately lost out to the AFAs with built-in data reduction.

The only way to benefit from an AFA’s data reduction features are to ensure applications and operating systems are not running host level compression or encryption. It may mean ripping out products like HyTrust and Vormetric. It may mean internal battles with DBAs. It may mean new terms and conditions in internal SLAs and storage chargebacks. The All-Flash Data Center sounds innovative on paper, but implementing it means working across traditional IT divides of applications, servers, security, and storage.

There are some data types which are natively compressed. For example, all the current Microsoft Office file formats are compressed. Additionally, most image files are compressed. Traditional file shares full of PowerPoint files are not going to benefit from AFA data reduction. Generally these workloads have never rated high-performance storage, and because of the lack of reducible data, it will take more time for the cost per gigabyte of All-Flash storage to come down to a point to provide the necessary payback to justify migrating these workloads to flash.

Why did I go down this path? It was to point the potential limits of a disruptive technology. When AFAs were narrowly applied to certain workloads, there was a cost-benefit which accelerated their adoption. When they are applied more broadly, they hit organizational barriers to adoption. Perhaps these barriers mean AFAs do not fit the definition of a disruptive technology. However, in IT I see many “disruptive technologies” which ultimately force significant operational changes on IT organizations. That was true for UNIX, Storage Area Networks, Windows, Linux, and VMware. It will likely be true for All-Flash Storage, Software Defined Networking, and adoption of Cloud Computing.

Why is There Not More Scepticism on Climate Science?

I continue to be surprised at how many people, especially Millennials (who are supposed to be skeptical), take "Climate Change" as gospel, despite evidence of highly questionable, and in some cases fraudulent science, such as the math used in Mann's "Hockey Stick" formula, and other questionable science revealed in the East Anglia email leaks.

Here are the questions I pose to anyone on the topic:

• What percentage of warming is due to CO2 emissions due to the burning of fossil fuels?
• What percentage of warming is due to other man-caused reasons?
• What percentage of warming is due to changes in solar activity?
• What percentage of warming is due to changes in other natural reasons?

Given observed questionable surface temperature measurement stations, and a noticeable difference in surface station temperatures and atmospheric temperatures, do Climate Scientist's heavy dependence on surface temperature measurements lead to unreliable results?

Source: New study shows half of the global warming in the USA is artificial

Source: 7 questions with John Christy and Roy Spencer: Climate change skeptics for 25 years

Given many Climate Scientists claim solar activity plays no significant role in Climate Change, but other Climate Scientists claim the significant pause in global warming is due to a decline in solar activity, how trustworthy is the climate science regarding solar activity?

Source: New study claims low solar activity caused "the pause" in global temperature – but AGW will return!

Source: Tiny Solar Activity Changes Affect Earth's Climate

Given one can insert random numbers into Michael Mann's equation and still produce a "Hockey Stick" output, how trustworthy should Dr Mann's science be considered?

Source: Michael Crichton - On Michael Mann's Climate Temperature Graph

Given evidence scientist Keith Briffa selectively picked evidence to support his desired outcome, and discarded evidence which did not support his desired outcome, how trustworthy should Dr Briffa's science be considered?

Source: YAD06 – the Most Influential Tree in the World


Given evidence scientist Philip Jones stated he used Michael Mann's "trick" to "hide the decline" of late 20th century cooling to overstate warming in the industrial era, how trustworthy should Dr Jones's science be considered?

Source: Climategate reveals 'the most influential tree in the world'

Source: IPCC and the "Trick"

Given climate scientists refused to allow critical peer review of their research, and only allowed it to be peer-reviewed within their tight circle of fellow climate scientists who believed the same way they did, how trustworthy should their science be considered?

Source: The tribalistic corruption of peer review – the Chris de Freitas incident

Given climate scientists working at government organizations refused FOIA requests for details of their research, how trustworthy should their science be considered?

Source: Climategate: James Hansen Finds Complying with FOIA To Be Too Much of a Burden


So there it is. Why not more skepticism, not that temperatures are rising, but skepticism of the science? I have said repeatedly, Climate Science is a Social Science, not a Physical Science. It is more about computer methods and curated data, and less about measurement. And other Social Science is held to much greater skepticism than Climate Science.

UPDATE:

Now there is this. The data used to dispute the "pause" in Global Warming is in dispute. By definition, science based on data that is in dispute cannot be considered "settled".

Exposed: How world leaders were duped into investing billions over manipulated global warming data

"True" Private Clouds

Wikibon is talking about "True" Private Clouds. I think their definition is too narrow, and gets into the weeds. It misses the true customer of a "true" private cloud. And there are two customers. The first is the organizational customer that purchases a private cloud. The second is the internal end-consumer of cloud services.

To Wikibon's credit, the definition of "Private Cloud" is an issue that needs to be addressed. In my career I have seen too many organizations overuse the term "Private Cloud". I have seen a VMware cluster deployed on disparate hardware with no upper level cloud management platform called a private cloud. I have seen converged infrastructure, acquired but managed identically to non-converged infrastructure (as discrete components each managed by their functional staff) called private clouds.

Converged infrastructure plays a role in a private cloud, be even that term is challenged. I have seen disparate servers and storage, purchased separately at different times, cobbled together and called converged infrastructure after the fact. I have also seen single-SKU converged infrastructure broken apart, support for component infrastructure separated, and individual components upgraded on different life-cycles.

From an operations perspective, I have seen mature IT organizations in large enterprises provide similar levels of managed services as traditional managed service providers. I have also seen the converged infrastructure single-support model dramatically fail organizational customers, and provide no better single support that that provided by an reseller or managed service provider.

If the goal of a "true" private cloud is to provide a similar level of service offering to internal end-consumers they receive from a public cloud, but with higher levels of compliance and data sovereignty, then much of the detailed requirements Wikibon mentions are not necessary. As long as the organization can provide an offering to internal end-consumers which is competitive (on cost,  ease of consumption, and reliability), it should meet the definition.

Here are what I believe are required of a "True" Private Cloud:

• Acquired in consolidated units of management, virtualization, compute, network, and storage with common amortization, and common life-cycle management.
• Components supported as an integrated whole, with a single number, first-call support model, and escalated support abstracted from the internal end-consumer.
• Compute, storage, network, and virtualization managed as a single entity by a single, cross-functional team.
• Provisioned and managed via a cloud management platform (CMP).
• Consumed by internal end-consumer as a shared resource in logical, not physical increments, i.e., VMs and GBs.
• End-consumer offerings include multiple performance and data protection SLAs.
• Provides charge-back to internal end-consumers.
• Provides the Private Cloud operator performance, capacity, and licensing budgeting of the infrastructure; performance metering and capacity measurement to manage over-subcription, prevent over-consumption (especially of performance), and allow for elastic performance and capacity scaling; and provide built-in performance and capacity planning for predictable infrastructure growth.
• Managed by high IT maturity organizational customer IT staff, or optionally part of a managed services offering  that does not require organizational customer IT staff to manage.
• Financed to organizational customer either through capital purchase, capital lease, operational lease, capacity lease, or pay-per-use offering.

Some organizational customers will want to capitalize the "True" Private Cloud and manage it themselves. Others will want to basically rent the whole stack to include the software, and have it managed for them. But the common denominator should be how the internal end-consumer consumes the offering. It should look, feel, and cost as much like the public cloud as possible.

U.S. Cyber Command's Requirements Demand Warrant Officers

Yesterday there was a hearing in front of the House Armed Services Committee, "Outside Perspectives on the Department of Defense Cyber Strategy".

Some of the points brought up were about the personnel management of military cyber warriors. This is a challenge, because "cyber" (BTW, I HATE the term) is both an infrastructure (i.e, IT Infrastructure), and a domain (Information Warfare). It is an area where both warriors and janitors walk, more akin to urban warfare than other historic domains.

Since the late 1980s, the military has treated IT as an area where COTS technologies should rule, to both increase the productivity of the military, and to reduce operating costs. At the same time, the PC and client-server boom of the 1990s drew skilled IT technicians from the military to the higher paying civilian sector.

Through the 1980s, the military, had its own data, uniformed, processing specialists. The father of a high-school friend was a Technical Sergeant in the Air Force and a Burroughs mainframe programmer.  In the 1990s, most of the programming positions were either converted civil service, or outsourced to contractors.

The second wave occurred in the 1990s with the decentralization of IT acquisition, management, and support from central service commands (i.e., Air Force Communications Command) to the local military bases.  This was followed with A-76 studies converting many base level IT jobs to a combination of civil service management and contractor work forces.

The result of all of this is the military lost its uniformed expertise in information technology.

Fast forward to today, and information infrastructure is as much a domain in warfighting as the seas and the air, yet the military is left without the skills in uniform which correlate not only to captains of ships and pilots of airplanes, but also to the technicians, operators, and maintainers. As a result, the military has once again centralized IT acquisition, management, and support, and is once again filling positions with uniformed personnel.

However, IT skills is unique in several ways. They are perishable. Old skill requirements (i.e., Novell NetWare, UNIX) become obsolete and unneeded, and are replaced with new skill requirements (i.e., Windows Server, Linux). To ensure quality, they require validation (i.e., IT Certifcations). Because they are COTS based, they are inexpensive compared to unique military skills. They are fungible and readily transferable to the civilian sector.

Another unique aspect of the military is ab initio training. The military will take someone from high school with the appropriate aptitude, enlist them, and train them up to a level of reasonable, beginners level, productivity. It then will use on the job training and continuing education to build expertise. In the case of an in demand skill set, this creates issues with retention. This is a bigger deal than a military turbine engine mechanic--there are only a handful of airlines needing them. But almost every organization needs a Windows administrator.

Then there are the challenges. The military needs, smart, highly skilled, problem solvers for day to day operation of the IT infrastructure. The military information infrastructure is more likely to be attacked both in peace and in wartime, but rapid recovery is critical in wartime. Poor retention hurts this need. The military needs deeply skilled, highly experienced IT technicians. But the need for operational managers is not that great, so the college educated, commissioned officer corps is not the appropriate career path for an IT technician. Something else is needed.

The military position of Warrant Officer is that of an technical specialist. Historically, the technical expertise came from experience serving in the enlisted corps.  In modern times, the Army uses Warrant Officers as helicopter pilots and trains them to the appropriate level or technical expertise.

Warrant Officers can serve as highly skilled individual contributors or as first level managers. It would seem a perfect career path for an enlisted military IT specialist. Tie it to certifications, and perhaps an Associate Degree, along with a service commitment and a retention bonus.

On the commissioned officer side, the career plan should be more on IT architecture, Information Warfare and advanced academic education. College educated officers would start focusing on both supervisory roles, and architectural roles. Then the focus should be on an advanced degree in the appropriate field of study. From there, moving to an Information Warfighting planning role, followed by the appropriate mid-career professional military education. Cross flow between related fields such as military intelligence would also be appropriate, however, this should be treated with care, as military intelligence often recruits from liberal arts studies such as history, foreign language, and political science. A cross flow program should not disrupt either the military intelligence corps, or the information warfare corps. Finally, the Joint Forces Staff College should create a dedicated Command and Staff school for information warfighters, with the goal of creating cadre of information warfighting leaders for all of the services.

Ultimately, the combination of a cadre of commissioned information warfighting leaders, combined with a corps of highly skilled warrant officer information warfighting specialists, would go a long way towards developing the cyber warrior force our nation requires.

A Reply to Chris M. Evans' "The NetApp Conundrum"

Storage blogger Chris M. Evans wrote a recent post on LinkedIn entitled "The NetApp Conundrum".

https://www.linkedin.com/pulse/netapp-conundrum-chris-m-evans

As a NetApp employee, and long-time member of the IT vendor industry, I have provided the following response.

I am having trouble resolving two points you made Chris. One is Data ONTAP is old (23 years, to be exact), and storage architectures only last 20 odd years. The second is clustered Data ONTAP is not Data ONTAP (the 23 year old one), but a new and different product created by merging some of Spinnaker's technology (acquired in 2003), with some of NetApp's technology in 2009. By my math, that makes clustered Data ONTAP six years old, and by your own calculation, it has 14 years of longevity left.

A few other points:

It is impressive HDS VSP's SVOS can run on a laptop. I can run a four-node clustered Data ONTAP cluster on my laptop.

The debate over the HA-Pair construct vs. a multi-node HA construct is an engineering and design debate, based on customer requirements, performance, time to market, predictable failure characteristics, and trade-offs--not ideology or perceived elegance. I would note VMAX engines are failover pairs for the same reason we use failover pairs in clustered Data ONTAP. It is also worth noting EMC changed the cache mirroring approach in Isilon with its Endurant Cache to a logical cache pair construct to maximize performance. Similar to clustered Data ONTAP, EMC XtremIO uses a cluster constructed of failover pairs, and Pure Storage use a failover pair scale up architecture similar to NetApp 7-Mode or EMC VNX.

True scale-out, distributed storage is interesting, but it presents challenges in developing fast, reliable, predictable failover. It is also very difficult to implement highly efficient data protection schemes, such as parity, double/triple-parity, and erasure coding in such an architecture. There is a reason Hadoop clusters, VSAN clusters, and Nutanix clusters use mirroring and triple mirroring for data protection. Nutanix's just announced EC is only for cold data.

What is happening today is almost all of the new all-flash array start-ups (XtremIO, Pure, Kaminario, Whiptail/Cisco, and Nimbus Data), and hybrid array start-ups (Nimble, Tintri, and Tegile), use log-structured filesystems, non-volatile memory and write coalescing, write to free-space, and parity RAID algorithms as the basic underlying technologies for their arrays. These concepts are more than 20 years old. NetApp built WAFL and Data ONTAP on these concepts more than 20 years ago because they worked. And they still work today, especially for NAND flash media. That is why NetApp continues to improve and develop Data ONTAP. Because the alternative to Data ONTAP looks a awful lot like Data ONTAP. Don't take my word for it--just look at the recent hybrid and all-flash storage players out there.

Thoughts on the HP Split

Too many people equate the PC business side of current HPQ as Compaq, and the enterprise side of current HPQ as the old HP. The truth is the old HP was nearly dead as a enterprise computing products company after spinning out Agilent and before acquiring Compaq. A quick look at HP's current technology portfolio shows much of it came in through acquisition. Much original HP technology has faded away. What is worse is much of HP's acquired technologies have been neglected to atrophy.

All of HP's current x86 server technology is former Compaq technology. The HP c-Class Blade System is a Compaq design which was in the works prior to the acquisition. HP's rack-mount x86 server technology is former Compaq. Engineering for HP x86 servers is done at the former Compaq facility in Houston.

Prior to the Compaq acquisition, HP's x86 server business was struggling to compete with IBM and Compaq's x86 server offerings. HP's x86 servers suffered from product quality issues, and little innovation.

HP's enterprise storage portfolio was a joke prior to the Compaq acquisition. Their organic mid-range system was sub-par, and they relied on an OEM relationship with EMC for their high-end solution.

Through the Compaq acquisition HP acquired the most sophisticated mid-range SAN platform of its time, the Enterprise Virtual Array (EVA). This was developed by Digital's StorageWorks division, which was working on the EVA prior to Compaq's acquiring them.

Within a decade, HP failed to innovate the EVA, and had to acquire 3PAR (and pay three times its market price due to a bidding war with Dell), to reinvigorate its mid-range storage line. HP also acquired LeftHand Network's SMB iSCSI systems to address the low end of its portfolio. HP still relies on an OEM relationship for the high-end, but now with HDS.

HP divested itself of the microprocessor business, ceding its HP-WideWord VLIW design to Intel to become the Itanium EPIC processor.

In the enterprise server space, HP's acquisition of Convex Computer gave it the SuperDome system, which originated as Convex's next generation Exemplar. While HP has iterated and evolved Convex's NUMA interconnect several times, there has been no net-new high-end server design from HP. The SuperDome 2 simply marries the "Convex Exemplar++" interconnect with the Compaq c-Class I/O backplane. And the idea that the coming "x86 SuperDome" will be anything other than a niche system is not going to happen.

In operating systems, other than its "Ignigte" bare-metal provisioning technology, HP-UX has lagged technologically behind Solaris and AIX for two decades now. HP's "innovations" were to OEM Veritas filesystem and volume management technology.

In automation, HP acquired OpsWare, the best technology out there in 2007. But now all of the oxygen in data center automation is being sucked up by either VMware or OpenStack.

HP had an excellent managed services organization (it used to be headquartered here in Atlanta), but this organization was subsumed into whatever is left of the former EDS post acquisition.

So the only organic components of HP I see still having value are the 30% of HP Services which was not part of the EDS acquisition and HP's printing division. Hewlett-Packard Enterprise is little more than a publicly traded private equity fund, a holding company of various technology brands (Tandem/DEC/Compaq/3PAR/OpsWare/EDS), in the mold of CA Technologies. In that way, they are similar to IBM, which also has acquired and failed to maintain many technologies. The difference is, IBM's organic enterprise technology (Mainframe, POWER, DB2, etc.) is aggressively maintained.

I honestly think the HP PC/Printer spin out will never happen as envisioned. Instead, HP will likely sell of HP PC/Printer to a private equity company who seeks the printer division as a cash flow business, and sees the PC division as something they have to buy in order to get the printer business. They will likely sell the PC business to an ODM who seeks a branded entry.

Where was I?

Where was I? It seems everyone is answering this question.

I worked for Sun Microsytems at the time and was in the King and Queen building complex in Atlanta in a sales training class. There were no TVs, so we only go the news via cell phones and the Internet. But the Internet had ground to a halt.. As soon as it happened, I knew it was Bin Laden. I was convinced Bin Laden (not Iranian Hezbollah) was behind the Khobar Towers bombing, which killed five of my 71st Rescue Squadron mates in 1996. I felt it odd to be explaining Bin Laden (who I described that day as the closest thing to a James Bond super villain who actually existed on this earth), continuance of government, and SCATANA to my coworkers. It was like I was in on everything which was happening and everyone else was blind. Somewhere in there I called my Reserve unit in Alabama and let them know if they needed me I could be ready and down there in four hours.

At some point someone said Sun's New York sales office was in the World Trade Center (floors 25 and 26 of the South Tower, the second tower hit, and the first to collapse). That realization changed the dynamic of our class. Within about an hour we got word the entire Sun office evacuated after the North Tower was hit, and everyone in the office made it out safely. Crazily enough, we pressed on with our class. We wandered like zombies to HoneyBaked Ham for lunch, came back, and I presented my portion of the training class.

That evening, after a couple of Jack on the Rocks at Joey D's Oak Room with my colleagues, I drove home. On the drive, I called a former 71ster (Darryle Grimes) stationed at the Pentagon. He had been in the Pentagon during the attack, but was far enough away to not actually feel the impact. He told me the Pentagon had gone to 24 hours operations and he had to be back there in a about an hour.

The second thing I remember is I was not able to sleep that night. That is only one of two nights in my adult life I was not able to sleep at all.

Politicizing Everything

The July 12, 2010 letter from five of the members of the Columbia Accident Investigation Board to Senator Barbara Mikulski is a piece of political, not scientific work, and can only be seen as an attempt to offer a fig leaf to an otherwise naked policy. I do not believe these five people just spontaneously decided to write this letter without being solicited to do so. First, it is a letter from only five of the thirteen CAIB members. Second, those members are claiming to speak on behalf of the CAIB:

"We would be glad to answer any questions that you or other members of Congress may have concerning the CAIB report and its application to today’s space policy issues."

Third, one of the five authors, Shelia Widnall was a Democrat political appointee, and three others, Steven Wallace, Douglas Osheroff, and John Logsdon were all Obama campaign contributors. Without knowing the opinions of the other eight members of the CAIB, these are just the opinions of individuals, and more accurately, potentially biased individuals. Fourth, the letter misrepresents some of the conclusions of the CAIB, specifically the following:

"The design of the system should give overriding priority to crew safety, rather than trade safety against other performance criteria, such as low cost and reusability, or against advanced space operation capabilities other than crew transfer."

"This conclusion implies that whatever design NASA chooses should become the primary means for taking people to and from the International Space Station, not just a complement to the Space Shuttle. And it follows from the same conclusion that there is urgency in choosing that design, after serious review of a "concept of operations" for human space flight, and bringing it into operation as soon as possible. This is likely to require a significant commitment of resources over the next several years. The nation must not shy from making that commitment."

Abandoning Ares I and Orion is being done for cost reasons, not for safety reasons. The primary means of taking people to the ISS will be the Russian Soyuz. Abandoning Ares I and Orion abandons urgency and does not bring a system into operation as soon as possible. It specifically abandons the significant commitment of resources over the next several years. It is shying away from the needed commitment.

Furthermore, the letter misrepresents the Ares I when it compares it to current EELV boosters. The first stage of the Ares I is based on the man-rated Space Shuttle SRB, of which 262 have flown successfully, a fact which escapes the "CAIB Five", because it makes the 34 EELV launches pale in comparison. The J-2X Ares I upper stage engine is based on the man-rated J-2 engine which had a 96% success rate, and despite a handful of engine failures, it had a 100% mission success record.

The Orion spacecraft is a simply scale up of the Apollo Command Module spacecraft. Scaling up an existing design is a proven cost and risk mitigation strategy, and was the same strategy used to develop the highly successful Gemini spacecraft. The Gemini capsule was based on an enlarged Mercury capsule, which allowed engineers to focus on the advanced features of Gemini rather than the capsule itself. This is no different from Orion. Much of the original aerodynamic work done on the Apollo Command Module still applies, so it means a safer, quicker, less costly solution.

Additionally the CAIB noted:

"It is the view of the Board that the previous attempts to develop a replacement vehicle for the aging Shuttle represent a failure of national leadership. The cause of the failure was continuing to expect major technological advances in that vehicle."

Ares I / Orion, by leveraging existing boosters, engines, and spacecraft designs, avoids the expectation of technological advances. Even the decision to move to a splashdown water landing was done to reduce risk and cost.

"With the amount of risk inherent in the Space Shuttle, the first step should be to reach an agreement that the overriding mission of the replacement system is to move humans safely and reliably into and out of Earth orbit. To demand more would be to fall into the same trap as all previous, unsuccessful, efforts."

While the Constellation project encompassed more than simply transporting astronauts to orbit, the Ares I / Orion system was focused only on this. The only additional demand was that a future uprated version of Orion, carrying four astronauts rather than six astronauts, be capable of flying to lunar orbit, be parked unmanned in orbit, and later return to Earth. Most of these capabilities would impact Orion's service module, not the manned capsule.

"Continued U.S. leadership in space is an important national objective. That leadership depends on a willingness to pay the costs of achieving it."

It is clear President Obama does not have the will desired by the CAIB, and Obama's decision represents another failure of national leadership. It also seems the "CAIB Five" no longer agree with the importance of U.S. leadership in space. This letter can only be seen as a dissent from Chapter 9 of the original CAIB report. The authors should be vigorously challenged not only on their statements in this letter, but also on their support of the original CAIB report's conclusions.

x86 Rises, Part 4: The emergence of Linux as a viable datacenter OS

Several years ago I drafted a white paper I called "x86 Everywhere". I started it in the fall of 2004, let it sit, and updated it in April 2005. It remains unfinished, but with the release today of Intel's Nehalem processor, I took a look at it again. Here it is:

Three trends could allow what I call "x86 Everywhere" to happen.

The third trend necessary for "x86 Everywhere" is the possibility of the emergence of Linux as a viable datacenter OS.

This seems less likely than high-end x86 servers at this point, but it is certainly possible in several years time, if the efforts of the Datacenter Linux project bear fruit. Windows on 32-bit x86 systems did not penetrate the datacenter, in part because the hardware was not 64-bit, the hardware was not scalable, and customers did not trust Windows with their critical data.

Today, the hardware is 64-bit, AMD Opteron is scalable to eight-sockets today, Intel is pursuing efforts that will likely address the scalability limitations of Xeon, both AMD and Intel are aggressively pursuing multicore chip strategies, and customers trust Linux in places they formerly only trusted UNIX. The result is a very real, industry standard ABI/ISA platform combination that scales from embedded systems, to an inexpensive developer platform (the PC), to midrange enterprise datacenter computers. This could be enough to cause a tipping point, creating a fundamental driver for the Datacenter Linux initiative. Such a change in the primary enterprise compute platform from RISC/UNIX to x86/Linux would likely be highly disruptive to the industry, and would rival the move of commercial computing in the early 1990's from proprietary minicomputers to SMP RISC/UNIX servers. Once established in the datacenter as a viable midrange enterprise platform, like SPARC/Solaris it becomes a straightforward scaling exercise for x86/Linux to establish itself as a high-end platform.

Finally, while not a trend driving large scale x86 adoption, there are other developments to consider. Intel has a virtualization technology, called Vanderpool on desktops and Silvervale on servers, that will help provide partitioning on its systems. AMD has also stated it intends to offer a virtualization layer, called Pacifica. AMD has also stated it plans to improve RAS features of its Opteron, and it is likely Intel will do the same with Xeon, using features it already offers on Itanium. Both of these key technology areas will improve adoption of x86 servers in the enterprise market.

How will this play out?

First, Dell's strategy is to only enter established markets, and to do so with a superior fulfillment system. For markets that are not at that point, Dell has used partnerships, such as its existing partnership with EMC. Dell also partners with Unisys to resell Unisys' 8-way Intel Xeon systems. Therefore the most likely path for Dell is to primarily continue the status quo, assuming four socket x86 systems and below represent the lion's share of the server market. If there is a need to address the greater than eight-socket x86 server market, Dell could expand the Unisys agreement beyond 8-way. If Dell expands into the Opteron market, and needs to address the greater than eight-socket x86 server market, it could partner with Newisys (also an Austin TX company).

IBM already is a player with its Enterprise X Architecture (EXA) for Intel systems. However, IBM has close ties to Newisys (the founder is ex-IBM, and the Horus chipset is based on similar principals to EXA), IBM sold its North Carolina based PC Server manufacturing plants to SCI-Samna, IBM has a strong presence in Austin TX, Newisys' home, and IBM has strategic agreements with AMD around CPU fabrication technology. It is possible IBM could offer the Newisys system in addition to its own EXA systems.

HP is committed to x86 in the four-socket and below space, and is a strong backer of Linux. If the x86/Linux platform gains momentum, it would simultaneously weaken Itanium sales. This would require a strategy change for HP, but such a change would be necessary to remain a viable datacenter systems vendor. To address this, HP could OEM a solution if needed to address a short term requirement. HP did this with NEC's high-end Itanium system before HP adapted its Superdome system to accept Itanium processors. Here the most likely partner would be Newisys, with similar Texas roots to the Compaq, whose former Texas offices server as headquarters for HP's x86 division in the post-merger HP. Longer term, HP's relationship with Intel could produce a high-end x86 system, especially given the common chipset Intel promises for Itanium and Xeon. In fact, HP's “Arches” system, the follow-on to Superdome, could easily accept future Xeon processors, given the common Itanium chipset. HP could also acquire a solution, but the most likely acquisition in this case would be Unisys. A Unisys acquisition would be defensive as well if Unisys had or was considering a significant Dell agreement.

Sun has some of the closest ties to AMD, and Sun has the technology to build large systems. Sun already plans eight-socket Opteron systems. If a significant market for larger than eight socket x86 servers emerges, Sun will have to decide how to address that market. However, balancing the high-end SPARC and x86 business would be a challenge for Sun. If the scalable x86 market shows great promise, the best technical solution for Sun could be an even tighter AMD partnership with technology sharing to allow common systems to be built with either AMD or SPARC processors. The potential for Sun to leverage common technologies such as coherent Hypertransport for SPARC systems as well as Opteron could offer considerable economies of scale. This could make the most sense in the post APL timeframe. A secondary solution, which also offers a near term solution, would be an OEM deal with Newisys. Sun has relationships with SCI-Samna, OEMing Newisys' two socket and four socket Opteron servers as the V20z and V40z, and Sun contracts with SCI-Samna to manufacture low-end UltraSPARC servers. A deal with Newisys around higher-end systems would also server to more strongly establish Sun in the Texas information technology community, clearly one of the top IT centers in the world, and the most important in the x86 business.

AMD's best interests are served if it does not depend on other vendor's chipsets for scalability. Therefore, offering a higher-end Opteron processor with more coherent Hypertransport links allowing greater glueless SMP scalability is the most likely path for AMD.

Similarly, Intel's best interests are served if it can offer everything needed to build a scalable server directly to the distributor. This is the shift needed to move high-end servers into the commodity space, and allow Dell to enter the market with superior logistics.

Based on all of this, a two-phased industry approach is likely. The first being server-vendor based proprietary scalable solutions (such as IBM's EXA, Unisys' CMP, and Newisys' Horus), followed by processor vendor solutions based on in-chip features.

Who is threatened most by x86 Everywhere? One could say Sun, who relies on SPARC systems for the vast majority of its revenues. However if x86 Everywhere happens, SPARC's installed base is still very large, and will not be replaced overnight. The bigger victim is likely IBM, who is trying to repeat Sun's SPARC success with its POWER architecture. In fact, assuming a Sun/AMD partnership could allow Sun to build SPARC or Opteron systems from common technology (i.e., memory controllers and memory subsystems, coherent Hypertransport MP interconnects, and common Hypertransport I/O bridges), SPARC systems could be continued as long as customer demand supported the design of SPARC processors.

The big loser in this appears to be Newisys. SCI-Samna's business model is two-fold: Contract manufacturing and OEM manufacturing. Newisys' low-end systems fit well in the OEM model, and SCI-Samna has had success selling these systems to its OEM partners. However, the high-end Horus systems do not fit the OEM model. Several have tried OEMing datacenter servers, and few have succeeded. In the late 1990s, Unisys OEMed its x86 CMP system to both Dell and Compaq. The Dell OEM lasted only months. Dell realized a 32-way datacenter server did not fit its direct business model. Compaq's deal lasted a little longer, but it too abandoned the OEM arrangement. Other OEM deals include HP's OEMing of NEC's first generation Itanium system, which delivered few sales. The most successful OEM deal of datacenter servers appears to be Bull Worldwide's OEMing of IBM's pSeries servers, but this arrangement created significant channel conflict for IBM in europe, and seems to always be in danger whenever IBM announced a new generation of RISC/UNIX servers. Fujitsu's deal with Siemens is not considered as an OEM deal here because it is really more of a partnership. The Fujitsu-Siemens model is worth considering by Newisys, as it is a successful model of a business relationship between a high-end server manufacturer and a IT solutions provider. The most likely target customers for Newisys' Horus system are IT integrators such as EDS. IBM has a high-end x86 server in its product portfolio. EDS does not. IT integrators can provide the professional services required in selling such systems. Also, because this would be an OEM arrangement, there is the opportunity for greater margins and services to the IT integrator, compared to deals which involve simply reselling an server vendor's product.

x86 Rises, Part 3: x86 Grows in Performance and Scalability

x86 Rises, Part 2: Decreasing Value of Big UNIX

x86 Rises, Part 1: The Background

x86 Rises, Part 3: x86 Grows in Performance and Scalability

Several years ago I drafted a white paper I called "x86 Everywhere". I started it in the fall of 2004, let it sit, and updated it in April 2005. It remains unfinished, but with the release today of Intel's Nehalem processor, I took a look at it again. Here it is:

Three trends could allow what I call "x86 Everywhere" to happen.

The second trend is the prospect of several vendors offering scalable 64-bit x86 systems large enough to meet most customer's workloads.

The desktop megahertz wars of the late 1990s and early 2000s between Intel and AMD drove x86 performance at a rate exceeding Moore's law. This directly benefited Intel x86 server performance, making x86 servers available for larger workloads. At the same time, enterprise applications were being rearchitected to multi-tier web-based applications, requiring deployment of additional web and application servers. RISC still had advantages over x86 in this environment, as running Microsoft Windows on x86 servers required the purchase of client access licenses (CALs) for each discreet user. This was extremely expensive for emerging self-service web-based ERP and CRM applications, but it was impossible for B2C ecommerce applications. Enter Linux. In the late 1990s, Linux became established as an entry server operating system, which unlike Microsoft Windows, did not require the purchase of client access licenses (CALs) for each user. Linux quickly became established as the web server OS of choice. The result was a positive feeback loop. Application server ISVs aggressively ported their J2EE appservers to Linux, and improved their clustering so their appservers would work well on clusters of low-cost entry x86 servers. ERP vendors quickly followed porting their application tier to Linux on x86. The low purchase cost of the Linux/x86 architecture was driven home by the dot-com bust and worldwide recession of the early 2000s.

At the same time as the desktop megahertz war, the smaller x86 chip manufacturers each tried to establish their products into a niche area. Via acquired Cyrix and focused in the “system on a chip” market for very low-cost desktops. Transmeta focused on very low power consumption chips for low-end laptops and embedded markets. AMD, long a player in the budget desktop market, decided to focus on the server market by designing an x86 architecture, called “Hammer” which addressed the weaknesses of Intel's existing Xeon x86 server processor, primarily the latter's lack of 64-bit memory addressing. The release of Hammer, branded as Opteron, forced Intel to follow suit with its 64-bit x86 technology, long rumored under the codename “Yamhill”, and branded as EM64T technology.

The emergence of a truly competitive x86 server processor marketplace is driving new innovation in x86 processors, as AMD tries to stay one step ahead of Intel, and as Intel tries to leapfrog AMD. Dual-core processors, improved power management, virtualization technologies, and other improvements are announced on a regular basis.

After the emergence of 64-bit x86 technology in 2004, in 2005 dual-core x86 processors were released. These two technologies have strong synergies. 64-bit addressing increases the size of the workload which can run on an x86 server, and dual-core processors increases the size of server which can be built with x86 processors.

With dual-core 64-bit x86 processors now shipping, and four-core 64-bit x86 processors possible in two to three years, four to eight socket servers may provide the capacity required for most customers' workloads. Beyond that, workloads requiring large, single system image servers (HPTC, large data warehouses, etc.), may be relegated to a niche market. Ordinarily, such a niche market could still justify large, scalable RISC/UNIX systems. But the market for large, single system image servers is not limited to RISC/UNIX. For some time, the scalable x86 market has been a targeted by some system vendors.

In the mid-1990s, Sequent, with its NUMA-Q system, was one of the first vendors of large, scalable x86 systems. Data General offered a very similar NUMA system during the same time period. Both of these systems provided very limited performance because of their architecture. Data General's system failed to gain significant market share, and was end of lifed not long after EMC acquired Data General. Sequent targeted decision support and data warehouse workloads with its NUMA-Q system and had some success. Sequent was acquired by IBM, and IBM released a more advanced x86 NUMA system which offered greater node to node bandwidth and large L4 caches to better manage inter-node latencies. In 2005 IBM released its third generation of x86 NUMA systems.

In the late 1990s, Unisys built a large, scalable SMP x86 system using a technology it calls cellular multiprocessing, or CMP. This technology was derived from Unisys' Clearpath mainframe systems. In fact, Unisys offers a version of its x86 CMP system which runs the Clearpath mainframe OS ported to the x86 architecture. Despite the mainframe heritage and mainframe variant of Unisys' x86 CMP systems, sales have not been strong. These systems were limited by the lack of scalability of Intel's x86 architecture, as well as the x86's lack of 64-bit memory addressing. Unisys now offers a second-generation CMP design, with simpler eight socket entry systems as well as large 32 socket systems.

Both IBM and Unisys offer 32-socket Intel Xeon systems, but both of these systems continue to be limited by the inherent lack of scalability in Intel's Xeon architecture.

The limits of x86 scalability changed with AMD's Opteron. Opteron is the first scalable x86 processor architecture. By virtue of its high-performance, coherent Hypertransport MP interconnect, Opteron is scalable in SMP design. Because of its 64-bit memory addressing, Opteron is scalable in memory capacity, with memory addressing balanced with processor performance. Four to eight socket x86 servers are no longer crippled with saturated SMP busses or inadequate memory capacity. Intel has followed suit with 64-bit memory addressing for Xeon, and a unique dual front side bus (FSB). But the dual FSB, while providing temporary relief to Xeon's saturated SMP bus, is actually designed for the soon to be released dual-core Xeon processors. Dual-core Xeons will likely once again saturate the SMP busses. Better SMP interconnects will be required for efficient scaling of Xeon systems to four sockets and above.

Over the next several years, x86 systems with eight-sockets and greater will become more prevalent. Newisys, a division of SCI-Samna, a major OEM manufacturer of AMD Opteron systems, is planning a 32-way Opteron chipset called Horus. Intel has promised future Itanium and Xeon processors will support a common chipset, allowing a next generation scalable Itanium server architecture to also serve as a scalable Xeon platform. This means traditional large scalable Itanium system vendors, HP, SGI, and NEC could enter the large scalable Xeon system market. The other possibilities are a higher-end AMD Opteron chip with more Hypertransport links allowing more scalable glueless MP topologies, similar to Compaq Alpha EV7's architecture, or the possibility of Intel introducing a scalable glueless chip to chip interconnect. It is important to note, Intel has access to the design of the EV7 interconnect and now employees the developers of the EV7's interconnect through an agreement with Compaq before Compaq was acquired by HP. Regardless, increased SMP scalability of x86 servers seems likely in the next few years.

Related Posts:

x86 Rises, Part 2: Decreasing Value of Big UNIX

x86 Rises, Part 1: The Background

x86 Rises, Part 2: Decreasing Value of Big UNIX

Several years ago I drafted a white paper I called "x86 Everywhere". I started it in the fall of 2004, let it sit, and updated it in April 2005. It remains unfinished, but with the release today of Intel's Nehalem processor, I took a look at it again. Here is Part 2:

Three trends could allow what I call "x86 Everywhere" to happen.

The first trend is the decrease in value of large, partitionable, RISC/UNIX systems.

All major commercial RISC/UNIX systems vendors offer large systems that can support large workloads, or can be partitioned to support many medium-sized workloads. The primary reasons for deploying a medium-sized workload in a partition on a large server are expected growth beyond the capacity of typical midrange servers, higher system resource utilization, system management efficiencies of server consolidation, and customer politics and preferences. Each of these reasons is coming under assault by the advancement of Moore's law, and as a result, the value proposition of large, partitionable datacenter servers is declining.

The performance improvements brought about by Moore's law over the last several years have outpaced customer workload growth, allowing midrange systems to handle the expected growth of most customer workloads. In addition, the price of midrange RISC/UNIX system has declined significantly over the last several years, starting with Sun's UltraSPARC III based V880, whose price point was then met by IBM with the POWER4-based p650, and HP's strategy of offering standard configurations of PA-RISC and Itanium midrange systems at very aggressive prices. Moore's law has caused system utilization to drop, as processors are now very powerful.

Traditional physical based partitioning, such as Sun's Dynamic System Domains and HP's Node Partitions (nPars) do not provide adequate granularity given the performance of today's processors. The result is the rise of software-based partitioning, logical partitioning, and virtual machine technology, which are portable to smaller, less expensive RISC/UNIX systems. In the case of purely software based partitioning technology, it is portable to other ISAs such as x86 platforms. For example, virtual machine technology is primarily being used on x86 systems via VMware's products. These shift in server partitioning technology are also decreasing the value proposition of large and midrange RISC/UNIX servers.

The recent emphasis in the industry for provisioning and system management solutions, along with policy-based computing solutions to manage large numbers of discreet servers has yet to significantly change the industry, however improvements in this area have improved the system management efficiencies of distributed servers. This, along with some of the inherent provisioning and management efficiencies of software-based partitioning technologies (shared network and disk resources) have resulted in a decrease in the relative value of large partitionable systems.

One should note, this decrease in value is real. It is not simply a customer perception. First, physical partitioning is simply too expensive a method to achieve partitioning in a server. Markets define prices, not vendors. Costs define margins, not prices. In a scenario with two otherwise equivalent servers, one using physical partitioning, the other using logical partitioning, the logical partitionable server will offer the vendor greater margins. Similarly, designing a server with physical partitioning which offers the same granularity as logical partitioning would likely be abandoned for having too high a cost. Second, customers really are moving workloads from previous generation large servers to smaller servers of the current generation, rather than partitions on larger current generation servers. In 1998 a Sun customer might consider paying the 50% price premium of an E10K over multiple E4500s. The value the 50% premium represented, primarily in growth capacity, justified the premium. Today the premium an E20K has over multiple V890s or V490s is so much higher (around 150% more), few customers can justify the value the E20K price premium provides.

The effect of this is a leveling of playing field between RISC/UNIX servers and x86 servers. Midrange RISC/UNIX servers are becoming simpler and cheaper. Midrange x86 servers have become more robust. RISC ISAs versus the x86 ISA is become a "Coke versus Pepsi" decision: a flavor choice.

Related Post:

x86 Rises, Part 1: The Background

Three types of people

I have come to a conclusion there are three types of people in the world:

Process people.

Idea people.

People people.

x86 Rises, Part 1, The Background

Several years ago I drafted a white paper I called "x86 Everywhere". I started it in the fall of 2004, let it sit, and updated it in April 2005. It remains unfinished, but with the release today of Intel's Nehalem processor, I took a look at it again. Here it is:

What is “x86 Everywhere”? x86 Everywhere is a concept that the dominance the x86 instruction set architecture (ISA) currently has on the desktop and entry server markets will expand into the midrange and high-end datacenter server markets, eventually reaching a tipping point, and displacing most RISC/UNIX platforms. Over time the x86 ISA establishes a monopoly in the datacenter similar to its current monopoly on the desktop.

The drivers for such a scenario are purely economic, but this does not refer to server acquisition costs. Instead it refers to the economic advantages a single, dominant ISA would bring to system vendors and independent software vendors. This is not the first time such a scenario has been speculated. In the early and mid 1990s, when Microsoft announced Window NT as a portable, multiplatform operating system for both RISC and x86, many speculated Windows would become the dominant operating system and programming application binary interface (ABI) from the desktop to large datacenter servers. A few years later, many speculated Intel's IA-64 “Merced” (later branded Itanium) ISA would dominate all computers, displacing RISC from the datacenter. Desktop PCs, entry and midrange servers running Microsoft Windows and Novell Netware, and high-end datacenter servers running UNIX would all use the IA-64 architecture. Despite this speculation, few put two and two together and speculated a Windows/IA-64 monopoly platform combination. The latest domination scenario proposed a few years ago was Linux would displace all UNIX variants. In this scenario, system vendors with their own UNIX variants would simply abandon their UNIX distributions and instead port Linux to their RISC architectures. This scenario is amazingly similar to the speculation about Microsoft Windows in the mid 1990s. Then experts suggested RISC vendors would abandon their UNIX variants to instead embrace Windows.

There is a huge difference with x86 Everywhere. The difference is the current installed base of x86 systems, and the current willingness of customers to use x86 systems for critical tasks. This is not to say other ISAs will exist. While RISC/UNIX established dominance in the datacenter in the 1990s, mainframes still exist, and while x86 is dominant on the desktop, the Apple Macintosh continues to be successful as an alternative platform. However, in this scenario, traditional RISC/UNIX systems are rendered to a smaller, niche market.

Three trends could allow what I call "x86 Everywhere" to happen.

I will cover those three trends in my next post.

On Power and Journalism

Another great quote. This time from Jonah Goldberg:

"But it’s worth remembering that government and corporations aren’t the only institutions that can abuse power. Factions, to borrow a word from the Federalist Papers, have a power all their own. When governments cave to that power, they become mere tools of bullies. And when journalists go along for the ride, there’s no one left to speak truth to power when that is what’s needed most."

An Excellent Observation on the Financial Bailout

Great comment from Mark Steyn on the Hugh Hewitt show last Thursday:

" ... what the government has been trying to do since October has been to re-inflate a credit bubble, to say that people should be able to get spectacular returns on mediocre assets as a permanent feature of life. And that is simply unsustainable. And my objection to what started back in mid-September is that no matter how much you pump into it, you cannot re-inflate a credit bubble, and you shouldn’t try. And that is something that if necessary, people have to take a bit of temporary pain ... "

Steyn is exactly right. We should be trying to ensure a soft landing on a reasonable bottom (i.e., preventing the crashing through a reasonable bottom into a worse situation), we should not be trying to reinflate a balloon with a huge gash in its side. That money is lost, and worse, takes with it more.

UPDATE: Another great comment by Steyn, where he calls the press "eunuchs to the PC sultans". That one's going to leave a mark (pun intended).

Thoughts on "Great Depression 2.0"

When I was in junior high (I think it was 8th grade), my Social Studies teacher (Mr. James) made everyone in the class interview someone who had lived through the Great Depression (that would be "Great Depression 1.0", or "Great Depression 29"). For Generation X, that generally meant interviewing a grandparent.

Mr. James gave us a list of questions to ask in our interview.

So, I took my Radio Shack monoural cassette tape recorder, and interviewed my grandmother, born in 1909 (or maybe it was 1908). The one thing I remember from that interview was one question: "What ended the Great Depression?" I still remember my grandmother's answer: "The wower" That would be "The War" for those who cannot translate a southern accent. "The War" refeedr to World War II. Now, "The War" didn't happen for America until twelve years after the stock market crash, and nine years after the election of FDR.

Wasn't there a New Deal? What about the WPA? The CCC? What, building the Hoover and Grand Coulee Dams didn't pull us out of the depression? Rural Electric Administration and the TVA? Nope.

Now, after we all did our interviews, we had to listen to them. For a week, we all listened to each of the interview tapes. And the one thing I remember is almost every subject answered the "What ended the Great Depression?" question the same way: World War II.

Is there a lesson in this? Perhaps. Perhaps the lesson is spending billions of dollars of taxpayers' money on make-work will not pull you out of depression, but spending billions of dollars of taxpayers' money on trucks, tanks, airplanes, and ammo will. Perhaps the lesson is economic problems are rarely solved quickly from the bottom up (i.e., jobs programs, consumer focused programs, tax cuts to individuals, etc.). Does it mean economic problems can be solved faster at the top (money supply, business lending, business taxes, etc.)? One could say the war spending was a direct subsidy to large American industrial companies, like GM and Boeing, and the jobs were a byproduct, that is, it was top-down. Certainly the decade-long economic downturn of 1973-1984 never adequately responded to the demand side economic efforts of Nixon, Ford, and Carter, and only recovered after Reagan's tight money supply and supply side focused efforts.

One thing I can say is, I can lean on that CCC-built rail at the Grand Canyon. I can use electricity from the TVA. They might not have pulled the U.S. out of depression, but one could argue we got something for the money, and some people were employed for some period of time.

But can we say the same thing about the current stimulus plan?

A stuck clock moment

Even Saturday Night Live gets it right sometimes:



Now I hear George Soros and Herb and Marion Sandler are not happy with the skit, so SNL has pulled the video from the official SNL site.

Supposedly, the skit now does not meet SNL standards, and they are going to "edit" the skit.

Wait a minute, I thought it was Saturday Night Live? Did I miss something? Editing a live skit after the fact?

I guess the new Lorne Michaels is George Orwell.