• Up to 1 TB of storage on a single chip
• Simple 3-D stacking for multiple terabytes
• Very low-power that helps extend battery life
• 20x faster writes than NAND flash
• Low-cost manufacturability - CMOS compatible process
• Half the dice size of current flash

The key is their simple electrical structure. They have a three-layer silicon-based material consisting of a top electrode, switching medium, and a bottom electrode.

Voltage across electrodes creates a filament across the electrodes that stores data. The filament is very small – on the order of 10 nm – so it can adjust to shrinking features sizes. Crossbar claims a 10 year retention at under 125°C and 10,000 write cycles for each cell.

10k may not sound like a large number, but it is 10 times the write performance of current multilevel cell flash. Using well-understood life-extending technologies from the flash world, the effective rate life will be over 10 times that.

Even better: the write speed is 20 times that of flash. That eliminates many of the issues that the bedevil flash controllers today. It also means the controllers should cost significantly less.

Crossbar is backed by Kleiner Perkins - one of the biggest and most successful venture-capital firms - and uses technology developed at the University of Michigan. Because it is CMOS compatible they will go to market first by licensing CMOS fabs for using the memory on system-on-a-chip and embedded device usage.

Embedded devices include smart phones, tablets and other consumer and industrial devices. Can you imagine a tablet with 8 TB of storage?

I can.

The Storage Bits take
There are variety of resistance RAM technologies vying for takeoff. Some promise very fast writes and long endurance but are not easily manufacturable.

Given the huge investments in current fab capacity – a state-of-the-art fab can cost $5 billion – the most important success factor is that it be manufacturable using today's technologies and materials. That's the approach that Crossbar has taken and it bodes well for their ability to come to market quickly at a competitive price.

Once they got off the ground we may be carrying phones with a terabyte of permanent storage. But their rollout strategy is conservative so unless Apple or Samsung buys them and pumps billions into the tech, don't expect to see consumer ReRAM products until 2016.

But its something to look forward to!

Comments welcome, of course. How would a 1TB phone change how your use?

When it comes to low latency and high bandwidth, the memory bus is hard to beat. But a terabyte? Diablo Technologies has announced one.

The secret is using flash instead of DRAM. Flash is much denser, lower cost, and uses much less power. And it's cheaper, too.

As a result, you can put 1 terabyte of flash on a standard-size DIMM. This moves in-memory computing from expensive technology for critical apps to a much more affordable technology for many applications.

How did they do it?

The TeraDIMM looks to the system just like a regular DIMM. The form factor and power are the same. There are no changes to the motherboard or applications, only a driver — available for Windows, Linux, and VMware — that makes the device look like either storage or system memory.

Of course, flash memory lacks some very important characteristics of DRAM. It wears out; it takes much longer to write; and it needs specialized controllers to manage all of its issues.

This is the secret sauce of the new product. An ASIC manages the flash and makes it look like either storage or extended main memory.

• Endurance: The product is designed to handle 10 full capacity writes — 10TB for a 1TB DIMM — every day for five years.

• Performance: 3-5µs write latencies.

• Capacity: Multiple modules can be pooled by the driver. Driver can broadcast rates to multiple modules for availability.

Use cases:

• Virtual machines: There is lots of read-only traffic in VMware. Placing virtual machines in main memory is significantly faster.

• High-frequency messaging: Low constant latency, even better than PCIe devices.

• Memcache: Uses main memory as a much bigger cache. Popular in hyper-scale clusters.

The Storage Bits take

There have been non-volatile DIMMs on the market before this. But this is the first one I've seen that that has all the elements needed for success: unique technology; economic advantage; top-tier VC and OEM support; and use cases in a rapidly growing part of the market.

No, you probably will not be buying these for your gaming rig. This is intended as an enterprise server class technology, and it will be priced as such.

But this brings new life to the concept of in-memory computing. Imagine 8TB of main memory to begin to see the possibilities.

Comments welcome, as always. How would you use a terabyte — or more — of main memory?

But now we've seen several quarterly declines in PC sales. How deep will the decline go?

Bounding the problem
This is NOT a one-for-one replacement of PCs with smart phones and tablets. There are hundreds of millions of people who can afford a smart phone or tablet but never a PC.

There is also a large population that requires the functionality – multitasking, large screens, exceptional compute and storage, and applications – that are only available on PCs.

But the battle lines are shifting: smartphones and tablets are getting more powerful, and new applications that enable new ways of working are being developed for them. Pilots replace 20kg of documentation and charts with an iPad.

But that's not all. Powerful server-side – cloud – applications, such as IBM's Watson, are also threatening the traditional PC platform. Imagine a physician dictating into his smart phone and a Watson-type service translating his dictation into finished and legible prescriptions, referrals and patient records. Why would that physician need a PC?

The grid
One of the early metaphors for personal computers was the idea of the fractional horsepower motor that put computer power where needed. But our electrical system uses centralized power plants provide electricity that we tap into when we need it.

Now imagine you are trying to sell generators. What is your market?

That is the problem facing analysts of the PCs future. There are substitute technologies, many new applications, a rapidly changing technology base and a growing global market. Plus the fact that PCs overshot the requirements of most folks 10 years ago.

The Storage Bits take
PC sales will continue to decline as more people understand that they don't need a PC to surf and email. HDTV screens will do double duty as monitors for people working - or playing - on their phones and tablets.

The long-term market for PCs are for the people who need the storage, computes and peripherals that only PCs support. Creatives. Corporate desk jockeys. Scientists and engineers.

Not grandmas, teenagers and mobile pros. Or most people.

Five years from now PC sales will bottom out at 185 million units - an almost 50% decline from 2011 - about the same  as 2003. Tablets and smartphones will be more than 4/5ths of all computers sold.

That's bad news for PC vendors. But the remaining buyers will be willing to spend more, so average sale prices will rise.

But for the rest of us mobile computers with all-day battery life and high-speed wireless networks will enable us to weave cyberspace seamlessly into our everyday lives. It's a brave new world.

Comments welcome, as always.  Tell me why you don't agree - or what I missed.

Wishful drinking  Start with wishful thinking - and you're doomed. Here are my favorite delusional quotes:

". . . consumers crave one experience across all of their technology." Consumers crave one experience? You better hope not because if they do Android is the likely winner.

"As technology moves from people’s desks to everywhere in their lives, it should become simpler, not more complex." Tablets and smartphones are simpler - that's why they're killing PCs.

". . . our strengths are in high-value activities, powering devices and enterprise services." Quick, name one successful Microsoft device that isn't a game console.

Reality check  Microsoft is an infrastructure and business user software company - and they are good at it - but they haven't beaten Linux. That is a real challenge and perhaps one they've decided they can’t win.

Microsoft is not a consumer product company. They've had some consumer products - the most famous of which is the Xbox -  but even that required billions of dollars in investment and numerous missteps before if finally turn a profit - just in time for the Wii and smartphones to shift gaming from consoles.

Microsoft has spent billions engineering products for enterprise use – a wise strategy since that is where the consistent margin is. They're also spending billions on cloud infrastructure and doing some very smart things better than Google. Enterprise and cloud are two sides of the same coin - and a natural market for all this innovation Microsoft keeps talking about. 

The Storage Bits take  Microsoft needs to focus on their enterprise and cloud technology and services instead of chasing after flighty teenagers. The Microsoft brand is many things, but cool isn't one of them. 

Microsoft's competitive strategy for markets that it didn't invent is simple: keep pouring money in and wait for the other guy to screw up. But there is a rich, diverse ecosystem behind Android and iOS that keeps inventing new and exciting options.  

And Google and Amazon aren't standing still on the cloud and services. Carving out a major market position given a late start won't be easy, but if they succeded it would pay for decades.

How about this for a challenge: develop a really good, easy to use consumer cloud storage service that offers massive storage, fast searching, versioning and guaranteed availability for a reasonable price. The masses are gradually realizing that all their digital data is risk and the big company that hits the sweet spot will reap decades of subscription income and consumer insight.

Yeah, it isn't cool - but neither are you, Microsoft. So go for it!

Comments weclome - as if I could stop you!  What are the challenges you think Microsoft is uniquely qualified to tackle?

A drive failed, reconstruction failed and vendor phone support was disastrous. All data was lost.

But the worst of it was that there was no backup. They believed that RAID5 would protect their data. They were wrong.

What RAID5 is for
RAID5 does offer some data protection assuming it works. But it's main purpose is to protect access to your data. This is why it is popular in enterprise applications where maintaining data access during a failure is of vital concern.

But these arrays are always backed up so that if there is a catastrophic array failure – a not uncommon occurrence – the data is still recoverable despite the interruption in service.

That's how it played out with the small company. After the drive fail they still had access to their data. But when they replaced the drive the rebuild did not go as expected. They were stuck.

If they had stopped there and made a backup they probably could've saved all their data. But they thought the RAID was there to protect their data. Oops.

The Storage Bits take
Most enterprise RAID today do not use RAID5 because the likelihood of a second failure during the rebuild – increasingly lengthy because of growing drive size – means that the likelihood of a second failure during rebuild is too high for comfort. Instead they use RAID6 - and hyperscale Internet services use even fancier erasure codes that can survive 4 failures.

Note that this does not mean a second drive has to fail: it can be as simple as an unrecoverable read error on a remaining drive that totally pooches the rebuild. Then you have to go to your backup - assuming you have a backup.

RAID was a wonderful advance 25 years ago. But the catchy name is no substitute for a backup and archive strategy.

Comments welcome, as always. That said, how do you archive your personal and small business data?

Teenager Jeff Clark grew up in Half Moon Bay and used to watch the surf breaking from his high school up on the hill. Finally we decided to go out and surf it.

His childhood friend Brian said he would call the Coast Guard and tell them where he was last seen.

So Jeff surfed it by himself. And the waves were world-class.

Thanks to an underwater rock formation, Mavericks - named for a surfer's dog - has some of the biggest waves in the world: 25 footers are common and can reach 80 feet during strong winter storms.

But for the next 15 years he was the only person to surf Mavericks. He tried to tell people about the huge waves - as big as Hawaii's Waimea Bay - and they thought he was nuts. Everybody "knew" there were no big waves in California.

Finally in 1990 he got a couple of Santa Cruz surfers - Dave Schmidt and Tom Powers - to try Maverick's big waves. They did, they survived, told their friends, and soon hundreds of people started surfing Mavericks.

Jeff Clark's lonely obsession was vindicated.

Danger and death
Thanks to cold water, big waves, rocks and currents, Mavericks is a dangerous place. Mark Foo, a top Waimea surfer, died there in 1994. Sion Milosky, another experienced big wave surfer, died in 2011.

Mavericks is, in the words of one surfer, "way gnarlier" than Waimea.

Why Mavericks?
I haven't seen a good explanation of why Apple chose the name Mavericks - cats hate getting wet - but some elements suggest themselves.

• Big waves. Steve rode several big waves - PCs, GUIs, digital media and mobile devices - to incredible success.
• Big bets. Steve made several bet-the-company decisions - the original Mac, the iMac, OS X - and many other major bets that went against popular opinion - the 68000, retail stores, Unix, music players, among others - like big wave surfers make every day. 
• Obsession. Imagine surfing some of the world's biggest and most dangerous waves for 15 years with no one watching. You just do what you do and wait for the world to catch up - if it ever does.

The Storage Bits take
What's in a name? The thing named isn't affected, but our cultural assumptions and expectations are.

Surfing is cool, like cats are cool. Definitely cooler than a new OS version.

But most of us will never surf, let alone surf big deadly waves. Hey, its marketing - and I'm cool with that.

Comments welcome, of course. This detour into a corner of storage we call history was informed by a great movie, Riding Giants, a gripping documentary of big wave surfing. Meet Jeff Clark and see what Mavericks is all about in the context of this extreme sport. Wikipedia also contributed.

In a recent essay, two former budget officials ask why the government can't play Moneyball with our tax dollars. It's a good question when we consider the size of and impact of government.

Health care. The government spends about half the healthcare dollars. Congress has made it a point to derail the most efficient use of government dollars. But with the advent of electronic health records - more than half of new records are electronic - we will soon be able to monitor and compare treatments for thousands of different ailments, at a much lower cost than limited double-blind studies.

Social welfare. One purpose of the US Constitution - "promote the general welfare" - is reflected in the spending of hundreds of billions of dollars every year for programs ranging from prenatal care to food stamps to the National Institutes of Health. But which of these programs actually works? We don't know - but we could if we collected and analyzed data.

Defense. President Eisenhower - a former general - warned America against the military-industrial complex that now costs over $700 billion each year. But Congressman routinely fight Pentagon efforts to spend more wisely, while the generals often support pet projects of little use.

Can we handle the truth?
Of course data is only useful if we act on it. On some issues - climate change, abortion, education, drug policy and more - it seems many people have made up their minds and don't care what the data says.

But that may be changing. Today's young people - hammered by the Great Recession, the loss of middle class jobs and gridlock in Washington - may take a more pragmatic approach. Stress - like the Great Depression and WWII - seems to focus Americans on solutions rather than ideology.

And right now we could use more solutions and fewer slogans.

The Storage Bits take
The reality based community is a minority in Washington DC and in state capitals. Our legislators happily get up and spout whatever nonsense their campaign contributors require - God won't let climate change happen! - and do so with a straight face.

But keeping government a data free zone is a recipe for disaster. Thanks to big data we cannot only spy on every American but we could also be ensuring that our government programs are more cost-effective.

It is up to citizens to insist that their Congressmen look at data and explain exactly how their plans will produce better outcomes. Most citizens won't, but those who do can help move America forward.

Comments welcome, of course.  If government wasn't important, why did the Founding Fathers lay down their lives, fortunes and sacred honor to found one?

Chicken and egg in 3-D
The BBC's report  on their decision had some interesting statistics. They noted that for the opening of the Olympic Games fully one half of Britain's 1.5 million 3-D sets tuned in.

But no other programming attracted anywhere near that fraction of 3-D ready customers. The best they saw was 5% penetration of 3-D capable systems.

That's weak.

2.5 years ago I gave 3-D a 70% chance of success provided they focused on glasses-free and mobile displays. That means either Apple or Samsung must take the lead - and neither seems ready to take the leap.

What does this mean?
What this means is that even the people who have invested in 3-D ready sets did not find the advantages of 3-D service compelling. After they'd seen it was only a nice-to-have, not a need-to-have.

Clearly, it wasn't cost: these people it already bought the systems. So what was the problem? The BBC's head of 3-D said viewers found it "hassly" and speculated

I think when people watch TV they concentrate in a different way. When people go to the cinema they go and are used to doing one thing - I think that's one of the reasons that take up of 3D TV has been disappointing.

Surely the BBC is continuing to look at the issues. It could be the quality of live 3-D wasn't that good. Or perhaps the "hassly" special glasses or limited viewing angles made it less attractive for group viewing.

Contrast this with the adoption of color TV back in the 1960s. Even though color sets were expensive and the color reproduction poor, once people got used to seeing their favorite programs in color there was no going back to black and white.

That is not the case with 3-D.

The Storage Bits take
If 3-D is going to be successful it is going to take a coordinated multiyear plan.

• Cost need to be reduced. Instead of looking at 3-D as a potential cash cow - like Sony did with Blu-ray - consumer electronic companies need to see it as a reason for buying big screen home theaters instead of watching everything on tablets and phones.
• Research has to continue to improve the production quality and the user experience of 3-D.
• 3-D production must continue to build a library of 3-D content.
• Most importantly, the industry must make glasses-free 3-D a priority. People aren't going to adopt 3-D until it is as easy as regular TV.

I think we're going to get there - I've been impressed with 3-D's potential - but this will be a marathon, not a sprint. 3-D cell phone displays will drive adoption. And a steadier flow of 3-D movies will continue to attract viewers.

Whatever it is, the industry hasn't cracked the code yet. But I hope they do.

Comments welcome, as always. What would it take for you to invest in 3-D: a 3-D smart phone or making it part of the 4k standard?

The new Mac Pro is all about configurability. Not within the tube, but as a system.

Professional users have a different set of economic priorities than consumers. These include:

• Reliability and availability. Uptime is crucial and the ECC DRAM a win.
• Performance. Professionals make more money when they get more work done. It doesn't take much more performance to justify a faster system.
• Specialized options. From 4K displays to fiber Channel networks to specialized I/O cards, professionals often invest as much or more in their peripherals than they do in their system processor.

What do some of these systems look like?

• A serious coder might have an 8-core system with five 30-inch monitors and two fast RAID arrays.
• A 4k video editor might have three monitors, a fast external array, Fibre Channel, a 4K optimized video card, a specialized control deck for editing and color grading and high-end audio and video I/O interfaces.
• A musician might have two or three displays, a fast array, multiple MIDI-based instruments and high-end audio interfaces.

What distinguishes each of these configurations is that the attached peripherals may cost more than a Mac Pro. This changes the economics of a system in important ways.

If you have $12,000 worth of peripherals, then $2500 for the computer is less than 20 percent of total investment. Not a big deal.

If you are a professional billing $100k annually, a system that reduces wait time by 5 percent can pay for itself in less than six months. A bigger deal.

Modularity
For many pro users the ability to add as many PCIe slots as needed will be key. Several Thunderbolt card cages are available today, making it possible to build configurations impossible with the current design.

And this means that once you've bought your PCIe cards and enclosures, you can upgrade your processor with much less hassle. Upgrade what you need when you need.

The Storage Bits take
The new Mac Pro is designed for these kinds of users. The abundant I/O capabilities make this the most configurable and expandable Mac Pro ever made.

It will find a small but appreciative and influential audience. For people who require specialized I/O and make money from their system, the new Mac Pro will be very attractive.

Which is not to say the new design is perfect. Having all of that I/O going through flimsy thunderbolt connections is not ideal. Nor will the "light on rotate" be useful when a half-dozen cables are plugged into the back of the Mac Pro.

But these are minor issues that enterprising accessory makers will solve. For the few people that need what a Mac Pro offers, they'll have a machine they can use for years.

Update: Seeing the objections to the term "mainframe" let me re-iterate and expand. The IBM 360/370 families were channel-oriented systems. For example, a mid-range IBM 360 model 50 supported up to 768 "I/O units" - disk, drum or tape drives - and up to 1,984 slow-speed devices - terminals, card readers and printers. While I doubt anyone went to these maximums, the point is that these were I/O, not CPU-centric, machines. Likewise with the new Mac Pro: it is a CPU with a lot of fast Thunderbolt I/O for external expandability.

Few appreciate just how fast Thunderbolt is. It makes it possible to edit 4k video on a 2012 MacBook Air. Having 6 of these channels on a Mac - supporting up to 36 devices, makes the Pro more like a mainframe than a current high-performance workstation. While I doubt that will satisfy everyone - anyone? - that's the basis for the "desktop mainframe" comparison. End update.

Comments welcome. Part of me wishes I was still editing videos so I could justify a Mac Pro.

But what if we stored human-readable document/photo/video copies? That is the premise of DOTS – the Digital Optical Technology System – that I learned about at the 2013 Creative Storage conference in LA Tuesday.

DOTS technology was developed by Kodak and ignored. In 2011, Group 47 acquired all DOTS patents and tech documentation from Kodak.

Group 47 plans to license the DOTS technology, and is also working to extend the DOTS patent portfolio with improvements and new techniques of leveraging the technology.

What is DOTS?
G47 says that DOTS is:

• Archival for no less than 100 years
• Non-magnetic
• Chemically inert
• Immune from electromagnetic fields including electromagnetic pulse (EMP)
• Stable in temperatures ranging from 15 - 150 F and humidity from 5% - 85%.

DOTS can survive almost anywhere humans would choose to live.

How does DOTS store an image?
DOTS stores data optically on a specially formulated, write-once tape in 15 micron-wide tracks:

These dots can store binary - machine-readable - data directly as the absence or presence of a dot represents one bit. But it can also store tiny human readable high-res photos or movie frames.

By breaking each frame into RGB - Red, Blue, Green - components, and each component into 8, 10 or 12 bit planes, a 4k image can be stored on a DOTS tape.

A camera can read each plane, combine them optically, and recreate the original movie frame. Since the data is read with a camera and not a computer, there is no dependence on exotic file formats or specialized editing apps.

Robustness
Computer image file formats are highly compressed - losslessly or not - to save space. But the compression that makes them efficient also makes them sensitive to bit flips in a digital file.

G47 took 24 frames of 4K JPEG 2000 Digital Cinema Initiative compliant images, and randomly flipped 13 bits of each of the JPEG images, a 0.001% error rate. Six of the 24 frames couldn't be opened and five of the frames had visual damage.

Since bit flips are endemic in magnetic storage, it clearly isn't suitable for 100 or even 50 year archives. DOTS solves that problem.

Infrastructure
G47 plans to deliver DOTS media and devices in LTO tape compliant form factors so current tape robots can use it. The optical images read by the tape drives will be converted to digital formats for computer use, but they can also be "read" by a camera and used without a computer.

Each LTO-sized cartridge can store 1.2TB and can be read at a faster than HDD 250MB/sec. And since it is optical, faster 2nd gen readers will be able to read 1st gen DOTS at 2nd gen speeds. Try that with magnetic tape!

The Storage Bits take
Optical storage is attractive because we understand how to manipulate light better than magnetism. DOTS is especially attractive because the data is human readable, dispensing with the entire computer data stack.

Since DOTS doesn't compress images its capacity requirements will be quite large compared to modern compressed images. But if media cost is low enough the ease of long-term storage will make it a bargain compared to magnetic tape.

But less efficient capacity will be a small price to pay for long-term human-readable data storage. Our digital civilization needs something more robust than simply copying digital data to new media every 3-5 years.

DOTS is the best answer yet to this critical problem.

Comments welcome, as always. I'm readying a review of another promising archive medium, the 1,000 year DVD. Images courtesy of Group 47.

In XORing Elephants: Novel Erasure Codes for Big Data, authors Maheswaran Sathiamoorthy, Alexandros G. Dimakis, Megasthenis Asteris, Dhruba Borthakur and Dimitris Papailiopoulos of USC and Ramkumar Vadali and Scott Chen of Facebook delve deeply into the issue. Technically it is related to work that Microsoft presented last year.

RAID repair problem
Standard Reed-Solomon erasure codes - the kind used in almost every RAID array today – isn't well suited to today's hyperscale demands. Back when RAID was new the alternative was disk mirroring. Compared to that RAID looked like magic.

Reed-Solomon codes suffer from an efficiency versus repair trade-off. In order to make a RAID5 or RAID6 reasonably efficient you need a wide stripe across at least 8 drives - and more is better.

But a wide stripe makes the time to repair a failed disk much longer. Data has to be transferred from every other disk in the stripe, using up scarce disk I/Os and internal storage bandwidth.

Replication nation
To avoid this problem early scale-out storage dispensed with Reed-Solomon codes in favor of double or triple replication. Using inexpensive disks rather than expensive arrays made this economical.

But exponential data growth has overwhelmed the ability of even the wealthiest web companies – Google, Microsoft, Amazon, Facebook and others – to build infrastructure fast enough and large enough to handle the tsunami of data. Something had to give and triple replication was it.

Major Web storage infrastructures are settling on a level of redundancy that standard RAID6 cannot approach. These systems can now typically survive the loss of up to four storage elements – disks, servers, nodes or even entire data centers – without losing any data. What is even more remarkable is that, as this paper demonstrates, these codes achieve this reliability with an overhead of only 40%.

Xorbas the Geek
Facebook has enormous storage problems. Their large analytics clusters can have 3000 nodes each storing approximately 15 TB of data.

That's 45 PB of raw capacity. For analytics. Whoa!

The data is stored in a highly scalable Hadoop cluster. The authors of the paper developed a new family of erasure codes called Locally Repairable Codes or LRCs that are efficiently repairable in disk I/O and bandwidth requirements.

They implemented these codes in a new Hadoop module called HDFS – Xorbas. They then tested this system in clusters on Amazon and within Facebook.

While the codes are slightly less than optimal in storage capacity, they recover quickly from failures while using much less network and I/O. Reduced network use makes them even more suitable for the geographic distribution of data, the next step in increasing availability.

The Storage Bits take
Good news: Facebook will be able to store massive amounts of data more efficiently than ever before. Bad news: so will the NSA and everyone else.

These codes aren't directly applicable to home and small office storage today since they require dozens of nodes to be efficient. But over time we could see small-scale, highly resilient storage that uses these codes as processors get more powerful and more people recognize the importance of failure-proofing their data stores.

Commments welcome, as always. Do you think the web industry is doing enough to reduce their environmental impact?

It isn't clear what is driving Apple's design interest in creating a tiny Mac Pro. It is way bigger than Intel's NUC which has hardly been a game changer.

Nor is it clear that placing a system unit on a desktop is all that desirable. With more than 10 cables it would look like a hedgehog.

That said there are some significant differences in the designs between the old Mac Cube and the new Mac Pro.

These include:

• Fan. The old Mac Cube relied on not very successful convection cooling. Adding a fan was a popular mod to avoid overheating during heavy use. Presumably the new Mac Pro won't have that problem.
• Expansion. The old Mac Cube had a couple of FireWire 400 ports and a modestly upgradable video card as well as a disk drive and some memory that could be changed. The new Mac Pro can add a dozen external PCIe slots to drive all kinds of accessories as well storage arrays.
• Sound. Once a fan was added to the Cube, the main benefit of convection cooling - silence - was gone. With a single large plenum and a slow moving fan the new Mac Pro should be very quiet. Fan better not break though.

Versus the current Mac Pro:

• Size. The current Mac Pro is a heavy beast that weighs over 20 kilos and a big footprint. No weight for the new MP, but given the aluminum frame and case I'd guess 2-3 kilos. And at 25cm high and 17cm wide it is tiny.
• Expansion. With 3 open PCIe slots the current Pro can accommodate eSATA controllers, media interface cards and add a 2nd graphics card, with the standard USB 2.0, FireWire 800 and Ethernet ports rounding out the list. With 6 Thunderbolt ports and 4 USB 3.0 ports the nominal bandwidth on tap is over 16GB/sec and the range of PCIe options a dozen times greater.
• Sound. Not mentioned by Apple, but if the cooling is as efficient as they claim, it should be quieter under load than the current box.

Use case?
Why would anyone care if a workstation is tiny? Since we haven't had one before, it isn't easy to imagine.

But here goes:

• Mobility. Have a screen at home and one at work along with a small portable storage array and you could - along with cloud storage - easily schlep your powerful workstation and its 3D simulations between home, work and even clients.
• Space. A single 4k display. A 6 drive array under the desk. Wireless keyboard and trackpad. 2 cables + power into the workstation and you have a very compact and powerful system that will appeal to people who make money from their computers but don't want their workspace defined by them.

The Storage Bits take
The new Mac Pro, with ECC memory, XEON processors and excellent cooling will no doubt be the most reliable Mac made. And if the Mac is your tool of choice it will be a very appealing upgrade from the current Pro or the flakier iMacs.

The prosaic issue of cable management won't be easily solved. Apple's glitzy "light up on rotation" feature won't be so useful once you've 3 or 4 cables plugged in. And the cylinder won't be nearly so pure when 8 mis-matched cables - USB, Thunderbolt and Ethernet - are bristling out the back.

Nor will the new Mac Pro solve the problem of OS X's aging file system and limited scalability. Windows 8 is way ahead here.

But for those who need a solid hardware platform, the new Mac Pro will be very attractive. It may even last longer than the current 10 year old case design. And it will be even easier to migrate peripherals with Thunderbolt than it is today.

The arguments for a new Mac Pro are still stronger than those against it. But this radical design may not be the right answer.

Comments welcome of course. I no longer have an excuse to buy a workstation. If you do, what do you think?

As I noted 6 years ago:

In the wake of 9/11 the government requested massive communications monitoring without legal authorization, which would have been easy to get. Only one telco, Qwest, refused after requesting, and not receiving, legal justification. That telco's then-CEO, Joe Nacchio, is fighting to stay out of prison after conviction on insider-trading charges, claiming on appeal that government retaliation led to less-than-expected results.

Whether you buy Nacchio's story or not it points up the danger to American liberty. A powerful executive branch, dependent telcos and a Congress - Ebay on the Potomac - running on "campaign contributions" from cosseted industries, and American liberty is on the trash heap of history.

Personally, I don't care if the NSA has access to my phone records and my Internet browsing habits. I am much more concerned that that access to that information be strictly controlled and its use legally constrained, with serious penalties for abuse.

Knowledge is power. And the abuse of power is one of the core issues and drivers behind our form of government.

Power is split between Congress, the executive branch, the judicial branch as well as the 50 state governments and numerous local governmental entities so that each element has someone looking over its shoulder to make sure, ideally, that it is behaving itself.

Which is the problem with the NSA's secrecy: because it's secret Americans have no idea how this information is being used. What safeguards are in place to control access. How the use of this information is legally circumscribed.

It doesn't help the NSA either. Someone claimed that over 100 potential terrorist plots have been aborted due to this program. If this is true, it is too bad that the NSA could not claim credit.

Of course the Obama administration will make the usual claims of national security and will, no doubt, pursue the leaker – who has done us all a great public service – to the full extent of the law. But in a free society an issue like this, which touches the life of every American, should be openly and loudly debated rather than hidden in the recesses of the national security community.

The Storage Bits take
The urge to escape accountability is a universal human trait. We do not help our democracy by carving out a huge exception for national security. Yes, some things need to be secret, but massive programs that touch every American aren't among them.

Did everyone in Congress and the security community honestly believe that such a huge program could remain secret forever? Then why even go down that road?

The obvious answer is: they were afraid that if the American people knew about it we wouldn't let us do it. Well, there's a price to be paid for living in a democracy.

That price is that in a democracy the citizens get final say. If, after robust debate, people decided that they would accept a little more terrorism in exchange for a little less surveillance, so be it.

It is the secrecy, not the program, that has created this firestorm. At some point, the national security community has to trust the citizens of these United States to make the decisions on such far-reaching programs.

Comments welcome, as always. For all that nattering about Obama as a liberal, he's only slightly to the left of Richard Nixon and most resembles a Rockefeller Republican, a now extinct species. And Joe Nacchio was sentenced to 6 years in the slammer.

I recently did a video for LSI, the long time maker of RAID and SCSI controllers and adapters, in which I interviewed LSI system architect and corporate fellow Robert Ober, who holds dozens of patents and is deeply knowledgeable about storage technologies.

How does flash work?
Flash stores an electrical charge in a quantum well in a floating gate transistor. The floating gate name comes from the fact that the normal transistor gate is isolated from the source and drain by an insulating layer of oxide. The gate "floats" between the two insulating layers.

The quantum well in the floating gate stores and electrical charge. In single level cell (SLC) flash either the absence or presence of charge gives us a single binary digit.

In multi level cell (MLC) flash there are four levels of charge corresponding to two binary digits. And in three level cell flash (TLC) there are eight levels of charge corresponding to three binary digits.

It takes about 20 V to write a flash cell. This voltage is created by on-chip pumps, which is why flash chips do not require a 20 V input.

With each write the high voltage places more charge into the insulating layers that protect the floating gate. As the charge in the insulating layers grows it takes longer and longer to write the cell.

Eventually, a write is no longer possible. When that happens the existing data can not be overwritten and is therefore preserved.

That's what flash "failure" looks like.

Other issues with flash
The video talks about more than how flash fails. For example, how should we think about the fact that flash is a wearing medium? How does write amplification work? What is the impact of data compression on write amplification?

These are among the other major issues addressed in the LSI video that you can watch here.

The Storage Bits take
Given the deep impact that NAND flash has had on the storage industry in the last five years, it is surprising about how little is generally known about the technology. Some of this is due to the desire to maintain trade secrets, but much of it has to do with a fear that knowledge would make users less comfortable about flash.

And users are uncomfortable about flash, though the discomfort is slowly dissipating with greater experience.

For example, early on the industry claimed that flash-based SSDs were much more reliable than disk drives. That wasn't completely true.

Yes, the most reliable SSDs are somewhat more reliable than HDD's, but vendors who threw together product's from spotmarket components turned out to be often much less reliable than disk drives.

Today we don't have any good alternatives to NAND flash, so the questions about how it works and how well it works are somewhat academic. But as new persistent storage technologies – such as resistance RAM technologies – come to market these issues will become more important to technical decision-makers.

Comments welcome, as always. LSI paid to create the video, but not for this post. What questions do you have about how flash works?

But now that disk drive manufacturing has been reduced to Seagate, Western Digital and Toshiba, what is the point of having a second source? PC vendors just have to trust that they'll have enough drives - and if they don't, well, too bad.

Thank the 2011 Thai floods for that new-found realism.

Innovation  Take the helium filled drive, for example. There is a lot of high technology that goes into building a container that won't leak.

Of course competitors will tear down the drive to understand the technology. But they'll see how successful the product is before deciding to invest in building a similar drive.

Western Digital, whose Hitachi Global Storage Technology subsidiary developed the drive, can ask buyers to pay a reasonable price given the economic benefits of higher capacity, lower power consumption and better performance.

Likewise Seagate can offer a 5mm thick hard drive knowing that customers will evaluate its business benefits, rather than insisting on a second source before they will incorporate it. Given the PC's sales freefall and the poor sales of Ultrabooks at their current MacBook Air price points, the 5mm drive will no doubt find many buyers.

The Storage Bits take   Several factors are at work:

• The global decline in PC sales forces PC vendors to get creative. Withering tablet and smart phone competition is seeing to that.
• Drive vendors have more market and pricing power because there are fewer of them. No PC vendor can afford to alienate the disk drive manufacturers.
• Finally, the entire disk drive industry is under threat from the rise of solid-state drives. If disk drive vendors want to be in business in another five years they have to get creative.

Maybe not so creative as to start producing disk drives for archive use to displace costly high-end tapes. But the end of second source tyranny is a boon not only the industry but to all consumers as well.

Comments welcome. What other changes to disk drives would you like to see?

Complicated storage isn't like a complicated network. With a network if you can't figure it out you can't go online. But complicated storage can cause all your data to go poof! Much more painful.

Drobo makes professional and pro-sumer storage arrays that are easy to manage. For example, you can mix and match disk drives because they don't need to be the same capacity. As the array gets low on space you can easily pull the smallest drive and add a larger drive to grow your array capacity.

Connected Data, maker of the brand-new Transporter back up appliances, has created a unique system that enables law and medical offices – who have stringent privacy requirements – and everyone else, to back up their data privately to a remote location. Instead of paying hundreds of dollars a year for a cloud service with slow recovery you buy the Transporters, load them locally at high speed and, as new data is added the data is copied securely and simply in the background.

With access apps available for all the major mobile and desktop platforms, the Transporter is a simple way to augment laptop, smartphone and tablet storage as well. Much more cost-effective than buying more flash memory.

Think of the Transporter as the Drobo of remote and secure backup. Without Jason Statham.

The Storage Bits take  The merger makes good sense. The same computer scientist and entrepreneur who started Drobo also founded Connected Data. Geoff Barrall also started high-end NAS box maker BlueArc - now owned by Hitachi Data Systems - in the early 2000s.

I expect that this merger represents a new strategy for Drobo: broadening the easy-to-use Drobo brand identity to more storage applications. Backup is still too hard for most consumers and many small businesses. Well-marketed the Transporter should be a winner.

Comments welcome, as always.  I first met Geoff in the early 2000s when he was starting BlueArc and consider him one of the most visionary technologists in the world of storage.

How? Foodler is a web-based service that's been around since 2005 and - the CEO told me - is profitable. They've automated the restaurant search and food ordering process.

And as of last month they accept Bitcoin as payment, automatically paying restaurants and delivery services in dollars at the current exchange rate. They even pay Bitcoin transaction fees.

Foodler makes money by charging restaurants a commission on each order. With no setup or monthly fees it is an easy and low-risk way for restaurants to get online.

The Storage Bits take  I'm intrigued by the idea of a virtual currency. Currency can be a store of economic value, and I'm professionally interested in all the ways, means and reasons we store data and other cultural artifacts.

Modern national currencies are no longer backed by gold or silver. Instead their value derives from the fact that they are accepted for products and services nationally and in some cases, such as the American dollar, worldwide.

Since currency works because it is accepted as a social norm, virtual currencies can succeed if they too are widely accepted. It is primarily a social issue - building trust and acceptance - and not a function of owning Fort Knox.

As the Internet has destroyed the business models of so many intermediaries by directly connecting us, I don't see any reason that a digital or virtual currency could not be successful. It won't be easy, and we've no doubt got a lot to learn about them, but whether a currency is backed by a government or an online exchange matters much less than it used to.

That's possible through creative Internet intermediation. The fact that Bitcoins can buy food marks a small but important step in the evolution of an online currency: sellers accepting a virtual currency without even knowing it.

Comments welcome, of course. No fiat or virtual currency changed hands in the preparation of this post.

The quote – "first they ignore you, then they laugh at you, then they fight you, and then you win" – illustrates where Bitcoin is today: people are laughing.

The excitement at the conference is like a low electric current running through the crowd. People sense there could be something great and lucrative here. The most successful and listened to participants project an air of calm and certainty.

The value prop
Several themes emerged around the reason for Bitcoin and why it – or another cryptocurrency – will be successful. For merchants the advantages are obvious and compelling.

• Cheaper than credit cards. Several BTC payment processors were offering their services for 1%. Compared to the 2%-6% charged by regular credit cards this is a bargain.
• Non-reversibility of transactions. Fraud is one reason credit card charges are so high. But once a payment is made with Bitcoin the money is committed and there is no way for the fraudster to get the money back.

Compared to earlier forms of Internet currency - Flooz, Netbeans et. al. - proponents point to the decentralized nature of the infrastructure. There is no single ledger that can be corrupted, confiscated or bankrupted.

The software is open source as well.

Issues
Bitcoins are analogous to cash. Lose your digital wallet and the money is gone!

Let a 3rd party hold your Bitcoins and if they abscond your money is gone! If you lose your private key your money is gone!

Bottom line: you have to protect your BTC as if they were cash because they are.

That said, there are strategies for protecting BTC just as there are for cash.

• Put Bitcoins into multiple wallets. You can only spend them once, but if one wallet goes pff-ft, the others are still available.
• Put your private key on a USB thumb drive - not your Internet-connected computer - and lock it in a safe deposit box. 
• Keep your Bitcoins close to your person. Don't leave them on exchanges or in pools.
• If you use a Bitcoin exchange, make sure they don't co-mingle depositor Bitcoins.
• While Bitcoins offer anonymity, portability and - through exchanges - exchangeability, you may not be able to get all 3 from a given service. Figure out what is vital to you and focus on that.

The zoo
There are about 20 companies exhibiting at Bitcoin 2013 and more that are in formation that aren't public. They fall into various categories.

• Exchanges. These exchange fiat currency - what we know as cash - for cryptocurrency - Bitcoin primarily - for each other. BitInstant is an example.
• Merchant services. Bitpay, for example, is a cash register in the cloud: merchants can accept Bitcoin and receive fiat currency the next day for a low 0.99% fee. Bitpay works across 30 currencies and, combined with non-reversibility, makes it valuable for merchants working internationally.
• Consumer services. Gliph offers an IM-style app that makes paying with Bitcoin as simple as sending a text. Coinbase https://coinbase.com can hook up your bank account so you can buy BTC online and they provide merchant services as well.
• Investor services. Tradehill offers banking and trading services for accredited investors, traders and institutions. Bitcoin Fund is another.

The Storage Bits take
Crypto-currencies have real advantages over current fiat currencies. If you accept the idea that what we call "money" is a social construct - i.e. its value derives from its exchange and storage utility - then you may be ready to start holding Bitcoin assets.

But, like holding cash, crypto-currencies have risks too. Values are volatile; security is a full-time concern; most companies are young and thinly capitalized; government regulation is rapidly evolving. All we can be sure of is that crypto-currencies will look very different in 5 years.

Comments welcome, of course. I'd like to hear about experiences readers have had with Bitcoin.

Today the value of Bitcoin and other digital currencies is more volatile than Americans are used to. But with Amazon and eBay looking at accepting them, that could change.

If that seems unlikely, recall that much of what you use now as "money" is simply electronic transfers: credit cards; debit cards; PayPal. Now, grasshopper, are those more "real" than Bitcoin?

The bad old days

Digital currencies are like how the US currency system used to work, before we had a national dollar.

Local banks issued its own currency supported - in theory - by the deposits of customers. To redeem the currency you'd go to the bank and exchange the notes for coin. When business crashed people would "run" to the bank to exchange their notes for specie - gold and silver coins.

Since banks borrow short term and loan long term, they would often run out of coinage and close - often costing depositors their life savings - which was Very Bad for business. That's why the US has a national currency, a Federal Reserve Bank and insures bank deposits (FDIC).

Digital currencies have none of these protections. But maybe that won't matter if the utility of them is greater than the fear that they'll become worthless.

How would that work?

"Gold bugs" advocate going back on the gold standard rather than letting the dollar "float" against other currencies. After all, advocates contend, without gold the dollar isn't backed by anything at all.

And yet the dollar remains the worldwide currency of choice, not only for B2B but as a store of value and convertibility as hard cash. Proof: most US currency circulates outside the US - Americans prefer credit cards.

Since the US dollar isn't backed by gold, and since the Fed can loan as much money as it wants to banks that can use it as reserves against loans - if only they were making loans! - why do we ascribe value to the dollar? Global acceptance and ready convertibility are two major reasons.

Which is where the value proposition for digital currencies makes the most sense. So can a digital currency replace - or at least supplement - national currencies? Yes.

The Storage Bits take

That isn't much different from what we used not so long ago - or what we use today. Digital currency is the new frontier in more ways than one: the 19th century dressed up in 21st century tech.

I hope to have more to say about it because I'm attending a Bitcoin conference that starts today. If you see me, say hi!

Comments welcome, as always.  Would you use a virtual currency? Would you put your life savings into it?

Note: Another version of this post appeared earlier on StorageMojo.

Not for me. I was happy with the performance of the Mac Pro, although I did upgrade it. I craved more flexibility, not performance, which is why geeks are mostly surprised by the popularity of tablets — and I'm not.

Case in point: Video editing. The reason I had the big Mac Pro was to edit video, although its stability — an Intel workstation motherboard, ECC RAM, ample cooling — haven't been equalled by any newer Mac I've used.

While I hire a professional for video editing now, I still do some at home. And I really can't tell the difference between editing on the Mac Pro and editing on the MacBook Air.

That's progress.

Specsmanship

The Mac Pro had 2 dual-core 2.66GHz Xeon processors, an upgraded video card, a 10K RPM WD velociraptor disk, a two-disk RAID, and 10GB of ECC RAM. The new MacBook Air has a dual-core i7 processor running at 2GHz, Intel's HD 4000 graphics, a 500GB SSD, and an external four-drive Thunderbolt array.

The MacBook Air also has a 2,560x1,440 Thunderbolt display and USB 3.0 ports. And when it's time to travel, nothing beats slipping the MacBook Air into a briefcase — no syncing!

Geekbench scores

The Mac Pro with four cores achieved a Geekbench score of 5,873 in 64-bit mode. The dual core i7 MacBook Air achieved 7,644, a 30 percent increase over it it's hulking predecessor.

While the MacBook Air is only dual core, Intel's Hyperthreading gives it two more virtual cores. Looking at my system's test results demonstrates that for many benchmarks it really works, giving the system the performance of more than two physical cores.

Other MacBook Air features play a role. The system bus speed is significantly higher, the L1 cache — which the MacPro didn't have — is infinitely larger, the L2 cache is the same size, but it's on-chip. Main memory is two times faster, the standard VRAM is larger, and the total system bandwidth is significantly greater.

I have to make do with 8GB of RAM on the MacBook Air. But the usually — though not always — snappy 500GB SSD reduces paging overhead, so the lesser capacity is rarely noticeable.

If you compare the size of the motherboards on the two systems, well, there is no comparison. The MacBook Air motherboard is tiny,smaller than an iPhone. There's a lot less fan noise as well.

All this in a system that weighs 8 percent of the original. And costs less.

The Storage Bits take

It took me a while to believe that my tiny MacBook Air could actually be faster than my workhorse Mac Pro. Was my memory playing tricks on me?

But when I sat down and compared specs, it became clear that in the last six years, the pace of technology has given me my Mac Pro in a slim, stylish, 3-pound case with a display, the keyboard, and a very functional trackpad to boot.

Our perception of what we need in a computer changes much more slowly than the actual technology. That's why tablets are popular: We're able to put the technology that people need and want into lightweight, portable, and functional systems. They have more power, ease of use, and battery life than most notebooks did 10 years ago. No wonder people love 'em!

While desktops and notebooks aren't going away, the tablet will be the leading platform for the next eight to 10 years. Perhaps in 2018, they'll even be fast enough for me.

Comments welcome. Have you switched to a smaller but faster system lately? Fun fact (for me, anyway): my #1 YouTube video has over 320,000 views.