Friday
Mar132015

Edition issues

Edition issues

I’ve been standing on the sidelines of discussions surrounding the Apple Edition Watch and the pricing, listening to points varying from the tech world’s point of view where value is derived uniquely from functionality, and their total incomprehension of markets that function differently, to the luxury watch world where value is derived from craftsmanship and the cost in person-hours, to the concepts from the fashion world surrounding things like Veblen goods and learning a lot.

I would just like to bring up a thought that occurred to me this morning about how much of the discussion surrounding the cost of goods and how this is such an incredibly limited method of analysis as a predictor of the eventual sale price of an object. This was underlined to me while reading a wonderful analysis of the videos Apple is showing about the manufacturing techniques they are using to produce the watches.

What this signaled to me is that there are complexities, costs and investments in the manufacturing process that go far beyond the raw materials costs that need to be accounted for. Granted, for some of these systems, Apple is working at such an incredible scale that these inputs can sometimes be marginalized when considered on a cost per unit basis, but the Edition presents a special case which will clearly never be production at the scale of any other product made by Apple.

And there’s one more thing…

The elephant in the room is simply this: It’s made of gold. Gold is both incredibly valuable on a price/weight and is also universally exchangeable. Many of the components in a modern smartphone, like individual chips and so on are probably higher value on a cost/weight valuation, but they are only valuable to the greater market when assembled into a final product.

Which means that it’s very likely that there is an entirely separate production chain and set of facilities set up specifically for managing these new risks, which brings the investment on a cost per unit up even higher. This also means more in depth security and background checking on the personnel that will be working in these facilities.

Gold as a major component to a product represents a hugely complicated security risk at all points in the production chain. This is an incremental cost that needs to be addressed from the source where gold is purchased and then transported to the factory where the gold is melted, converted to flattened ingots and then into blanks. From there the blanks will be taken to the facility where the machining is done (I find it doubtful that these processes are done on the same site), noting that anything dealing with machining produces swarf only in this case, the swarf is valued at $800-$1000/ounce rather than the commodity pricing of aluminum. Not to mention that even if I recover a couple of pounds of aluminum by putting sweepings in my pocket, the available marketplace for reselling it remains limited.

Then we have the additional security through all of the following stages of stocking and transporting and then additional security at the store level. This is a non-negligeable cost factor that pretty much all of the discussions are ignoring. The watch people ignore it because it’s second nature to them and therefore obvious, the tech press ignores it because it’s so outside of the scope of the way the world works for them.

Remember, like all products, the cost is greater than the simple sum of the parts.

Tuesday
Mar032015

Datacenter SSDs cross over the price/Gb Barrier

This is a bit of a head scratcher. Samsung’s latest datacenter SSD lineup is now in the same price range as comparable enterprise SAS drives.

According to the documentation, the high endurance models are good for 10 drive writes per day over the 5 year guarantee. The kicker? I just found this drive for 670€ on amazon.fr all taxes in.

Wow.

Tuesday
Mar032015

Back to backups (yet again)

In the world of information technology, nothing is static and lasts forever, especially best practices. I’ve been pointing out to clients for a while now that backups need to be rethought in terms of the “jobs to be done” philosophy and no longer thought of as “the thing that happens overnight when files are copied to tapes”.

Historically, backups served two purposes :

  • Being able to go back in time and retrieve data that is no longer available
  • Serve as the basis for a disaster recovery

Fundamentally, backups should really only serve the first point. We have better tools and mechanisms for handling disaster recovery and business continuity. Which brings me to snapshots. I have always told people that snapshots are not backups even though they respond to the criteria of being able to go back in time.

The hiccup is that snapshots that are dependent on your primary storage system should be considered fragile, in the sense that if your primary storage goes away (disaster), you longer have access to the data or the snapshots. However, just about every storage system worth its salt today includes the ability to replicate data to another system based on or including the snapshots themselves. This is a core feature of ZFS and one I rely on regularly. Many of the modern scale out systems also include this type of functionality, some even more advanced than ZFS like the SimpliVity implementation.

When are snapshots backups?

They become backups once you have replicated them to another independent storage system. This responds to the two basic criteria of being able go back in time and be on a separate physical system so the loss of the primary does not preclude access to the data. They become part of your disaster recovery plan when the second system is physically distant from the primary.

Disk to Disk to Tape

We’ve already seen the traditional backup tools adopt this model to respond to the performance issues around coping with the every growing volume of file data so that data can trickle over to a centralized disk store which is directly connected to tape drives where they can be fed at full speed. Exploiting snapshot based replication permits the same structure, but assigns the responsibility of the disk to disk portion to the storage system rather than the backup software.

The question I ask in most cases here is whether the volume of data involved justifies the inclusion of tape as a backup medium. According to the LTO consortium, LTO6 storage is as low as 1.3 cents per Gb, but this only takes into account the media cost. The most bare bones of LTO drives runs around $2,200, which bumps up the overall cost per Gb rather dramatically.

Assuming a configuration where we store 72Gb of data on tape (12 tapes), at the $80 cost per tape cited by the LTO Consortium plus the cost of the drive, this works out to about 4.3 cents/Gb. At current street prices, the 6Tb WD Red drives run about $270 which converts to 4.5 cents per Gb, not taking into account the additional flexibility of disks that permit compression and deduplication. Note that the 6Tb cited for the LTO numbers already includes compression where the 6Tb disk is raw before compression and deduplication.

Tape does have some inherent advantages in certain use cases, particularly long term offline storage, and does cost less to operate on a $/watt basis, but for many small to medium sized environments, the constraints for using it as a primary backup medium (especially when it is also the primary restore medium) are far outweighed by the flexibility, performance and convenience of a disk based system for daily operations.

Operational convenience of disk over tape.

Tape is a great medium for dumping a full copy of a dataset, but when compared with the flexibility of a modern disk based system it falls far behind. A good example that I use is the ability to prune snapshots from a data set to reorganize the space utilisation. In many systems, I use hourly snapshots in order to give users the a decent amount of granularity to handle errors and issues during the day. This also means that the unit of replication on a given filesystem is relatively small, permitting me to recover from intersite communications failures and not have to resend huge data sets that might have been interrupted. Then on the primary system I prune out the hourly snapshots after a week to leave one daily instance to be retained for 2 weeks. A similar process is applied to weekly and monthly snapshots. Where this gets interesting is that I do not have to apply the same policy on the primary and backup storage systems. My backup storage system is designed for capacity and will retain a month of daily snapshots, 8 weekly snapshots and 12 monthly snapshots. The possibility of pruning data from a set is something that is impossible to do effectively using tape technology, so tape is used for an archival copy that needs to be retained beyond the yearly cycle.

Files vs virtual machines

The above-noted approach works equally well for file servers and storage systems hosting virtual machines, especially if we are using a file based protocol for hosting the VMs rather than a pure block protocol like FC or iSCSI. In the world of virtual machines backup tools are considerably more intelligent about the initial analysis of the data to be backed up. Traditional file server backup is based on a two phase process of scanning the contents of the source, matching this against an index of data known to be backed up and then copying the missing bits. This presents a number of practical issues :

  • the time to scan continues to grow with the number of files
  • copying many individual files is a slower process with more overhead that block based differentials

By applying the snapshot and replication technique, we can drastically reduce the backup window, since only the blocks modified between two moments in time need to be copied. In fact there is no longer a backup window since these operations are continuous in the background of the file server.

Virtual machines in the VMware world maintain tracking journals of modified blocks (CBT) which enables the backup software to ignore the filesystem representation of the data and just ask for the modified blocks to copy since the last backup transaction. But again, if we are transmitting snapshots from the underlying storage system, don’t even need to do this. It is, however useful to issue VSS snapshots inside of Windows virtual machines to ensure that any inflight data in caches is flushed to disk before creating the storage layer snapshot.

The biggest issue with backing up virtual machines is the granularity of the restore operation. With only a simple replication, the result is a virtual machine with no visibility into the contents of its internal file systems. This is where the backup tools show their value in being able to backup a virtual machine at the block level, and yet still permit file level restores by peeking inside the envelope to look at the contents of the file systems therein.

The last mile

There are still issues with certain types of restore operations that require a high level of integration with the applications. If you want to restore a single email out of a backed up Exchange or Notes datastore, you need a more sophisticated level of integration than simply having a copy of the virtual machine.

But for the majority of general purposes systems, and particularly file services, the simple replicated snapshot approach is simpler and more effective, both from a cost and operational perspective.

Tuesday
Sep302014

The Cellular Hub

There has been an upsurge in articles and discussions around the wearable market in recent weeks after the Apple Watch announcement.

Some of the best thinking has come from Ben Thompson over at Stratechery, and John Gruber at Daring Fireball but I wonder if we are all parsing this through the restrictive lens of what we know and are familiar with. One thought is that the Apple Watch, a device that must be tethered to an iPhone, will perhaps be capable of becoming a fully autonomous device including native 3G, GPS etc. in the next few years.

I think that unlikely for a number of reasons. While Apple has accomplished miracles of miniaturization, the fundamental issue remains power autonomy. I don’t see battery technology making any leaps to 10x the current density that would allow a watch-sized device to run all of the radios for a full day and have space for some kind of SIM card.

They could save space by going the CDMA route and make the SIM card an intrinsic part of the device, but this requires large changes in the way the bulk of the world’s GSM/LTE technology is sold and deployed. This still doesn’t address the power consumption issue, other than freeing up space inside the device.

I think that the watch is the logical first step in the socialization of wearable technology because we already have context for the device. We’ve been wearing jewelry for thousands of years and timepieces for hundreds; it is a mature concept bifurcated into a utility market and a luxury market, where both exceed the utility needs of most people that just want to display the time.

The reason I wonder about other possibilities are the advances brought by iOS 8 that link all of your Apple devices into a small Bluetooth and WiFi mesh network.

Example: I have an iPad Retina at my desk attached to the (excellent) Twelve South HoverBar arm, serving as an ancillary display for Facetime, WebEx, Tweetbot, OmniFocus and so on. Yesterday, the iPad lit up with an incoming phone call while my iPhone was sitting in a pocket, thus the iPad became a fully featured speakerphone. This was done with basically zero configuration on my part other than signing into my iCloud account on both devices.

This got me to thinking about the utility of the phone device as the cellular conduit. We are used to the concept of “the phone”, including its heuristically necessary baggage like size, which is mostly dictated by the screen, and the form which is dictated by the use cases of alternately looking at it and holding it up to your ear.

If we remove the screen and leave only battery, radios and the crudest UI (on/off for example), a myriad of possible forms emerge. Imagine an integrated MiFi device that provides connectivity to a variety of devices around you – something that you could wear. This kind of device could be designed as a belt buckle for example, or a necklace, bringing an additional set of options to other surrounding screens. I no longer need an iPhone… An iPod Touch as a small screen device where I currently use the iPhone, an iPad serving the jobs requiring more screen real-estate, devices and screens enabling HomeKit, all of which become data and voice enabled by the presence of the cellular hub.

There is a competing thin-client concept that has been around for a while, but has been oriented towards enterprise devices, reducing computers to screens with no intelligence with content projected from a server. Think Citrix, Microsoft RDP, VMware Horizon View. I don’t think this is viable in this space since the latency imposed by passing Retina-quality display data over a wireless network is huge - fine for a mediated UI with mouse and keyboard, but not for a touch-enabled system that requires immediacy of reaction.

Current cellular devices claim a price premium over similar non-cellular devices, witness the iPhone vs the iPod Touch. You can get an iPhone 6+ for the extra battery performance, but retain all of the advantages of the one-hand manipulation by linking it to an iPod Touch. But why should I pay the premium for a iPhone with the big screen? If it’s going to live in a bag, why not something without a screen? And if I need it all the time, why can’t/shouldn’t I wear it?

By consolidating the responsibility of cellular communications to a single device, the satellite devices will be individually cheaper to acquire, and I would likely buy multiples for the various jobs to be done. As a quick example, the current 64Gb iPhone 6 sells for 819 € unlocked in France. A 64 Gb iPod Touch is only 319 €. At this kind of cost disparity, I can imagine buying multiple ancillary screens for various contexts. Apple would take a bath on the margins, but if you’ll pardon the phrase, they could make it up in volume…

This approach fits nicely with the idea of the Apple Watch as just another one of the screens that I have available to me, enabled by a cellular connected wearable that is always with me as well.

Thursday
Aug142014

Understanding the impact of scale-out storage

Scale-out has the ability to change everything

In the software-only space solutions like Datacore and Nexenta are really quite good (I have used and deployed both) and I still recommend them for customers that need some of their unique features, but they share a fundamental limitation in that they are based on a traditional scale-up architecture model. The result is that there is still a fair bit of manual housekeeping involved in maintaining, migrating and growing the overall environment. Adding and removing underlying storage remains a relatively manual task and the front end head units remain potential choke points. This is becoming more and more of an issue with the arrival of high performance flash, especially when installed directly on the PCIe bus. The hiccup is that you can end up in situations where a single PCIe Flash card can generate enough IO to saturate a 10GbE uplink and a physical processor which means you need bigger and bigger head units with more and more processing power.

So the ideal solution is to match the network, processor and storage requirements in individual units that spread the load around instead of all transiting through central potential choke points. We’re seeing a number of true scale-out solutions hitting the market right now that have eliminated many of the technical issues that plagued earlier attempts at scale-out storage.

The secondary issue with scale out changes the way you purchase storage over time. The over time part is a key factor that keeps getting missed in most analysis of ROI and TCO since most enterprises that are evaluating new storage systems are doing so in the context of their current purchasing and implementation methodology: They have an aging system that needs replacing so they are evaluating the solution as a full on replacement without truly understanding the long term implications of a modern scale-out system.

So why is this approach different? There are two key factors that come into play:

  • You buy incremental bricks of capacity and performance as you need them
  • Failure and retirement of bricks are perceived identically by the software

To the first point, technological progress makes it clear that if you can put off a purchase you will get a better price/capacity and price/performance ratio that you have today. Traditionally many storage systems are purchased with enough head room for the next 3 years which means you’re buying tomorrow’s storage at today’s prices.

So this gives us the following purchase model:

This is a simplified model based on the cost/Gb of storage but applies to all axes involved in storage purchase decisions such as IOPS, rack density, power consumption, storage network connections and so on. Also remembering that you might end up with bricks that still cost $x, but have 50% more capacity in the same space. A key feature of properly done scale out storage is the possibility of heterogeneous bricks where the software handles optimal placement and distribution for you automatically. For “cold” storage, we’re seeing 3Tb drives down under the $100 mark, but 6 Tb drives are now available to the general public. If you filled up your rack with 3Tb drives today, you’d need twice the space and consume twice the power than if you could put off the purchase until the 6Tb drives come down in price. For SSDs, Moore’s Law is working just fine as we see die-shrinks increase the storage density and performance on a regular cycle.

In some organisations this can be a problem since they have optimized their IT purchasing processes around big monolithic capital investments like going to RFP for all capital investments which means that the internal overhead incurred can be counterproductive. But these are often the same organisations that are pushing for outsourcing everything to cloud services so that storage becomes OpEx, but this type of infrastructure investment lives somewhere between the two and needs to be treated as such. Moving straight to the cloud can be a lot more expensive, even when internal soft costs are factored in. Don’t forget that your cloud provider is using the the exact same disks and SSDs as you are and needs to charge for their internal management plus a margin.

And on to the upgrade cycle…

The other critical component of scale-out shared-nothing storage is that failure and retirement are perceived as identical situations from a data availability perspective (although they are different from a management perspective). Properly designed scale-out systems like Coho Data, ScaleIO, VSAN, Nutanix, SimpliVity and others guarantee availability of data by balancing and distributing copies of blocks across failure domains. At the simplest level a policy is applied that each block or object must have at least two copies in two separate failure domains, which for general purposes means a brick or a node. You can also be paranoid with some solutions and specify more than two copies.

But back to the retirement issue. Monolithic storage systems basically have to be replaced at least every 5 years since otherwise your support costs will skyrocket. Understandably so since the vendor has to keep warehouses full of obsolete equipment to replace your aging components. And you’ll be faced with all the work of migrating your data onto a new storage system. Granted, things like Storage vMotion make this considerably less painful that it used to be, but it’s still a big task and other issues tend to crop up, like do you have space in your datacenter for two huge storage systems during the migration? Enough power? Are the floors built to take the weight? Enough ports on the storage network?

The key here is that in case of a brick failure in a scale-out system, this is detected and treated as a violation of the redundancy policy. So all of the remaining bricks will redistribute/rebalance copies of the data to ensure that the 2 or 3 copy policy is respected without any administrative intervention. When a brick hits the end of its maintainable life, it just gets flagged for retirement, unplugged, unracked and recycled and the overall storage service just keeps running. This a nice two-for-one benefit that comes natively as a function of the architecture.

To further simplify things you are dealing with reasonably-sized server shaped bricks that fit into standard server racks, not monolithic full-rack assemblies.

Illustrated, this gives us this:

Again, this is a rather simplistic model, but with constantly growing storage density and performance, you are enabling the storage to scale with the business requirements. If there’s an unexpected new demand, a couple more bricks can be injected into the process. If the demand is static, then you’re only worried about the bricks coming out of maintenance. It starts looking at lot more like OpEx than CapEx.

This approach also ensure that the bricks you are buying use components that are sized together correctly. If you are buying faster and more space on high performance PCIe SSD, you want to ensure that you are buying them with the current processors capable of handling the load and that you can handle the transition from GbE to 10GbE to 40GbE, …

So back to the software question again. Right now, I think that Coho Data and ScaleIO are two of the best standalone scale-out storage products out there (more on hyperconvergence later), but they are both coming at this from different business models. ScaleIO is strangely the software-only solution from the hardware giant, while Coho Data is the software bundled with hardware solution from part of the team that built the Xen hypervisor. Andy Warfield, Coho Data’s CTO has stated in many interviews that the original plan was to sell the software, but that they had a really hard time selling this into the enterprise storage teams that want a packaged solution.

I love the elegance of the zero configuration Coho Data approach, but wish that I wasn’t buying the software all over again when I replace a unit when it hits EOL. This could be regulated with some kind of trade-in program.

On the other hand, I also love the tunability and BYOHW aspects of ScaleIO, but find it missing the plug and play simplicity and the efficient auto-tiering of Coho Data. But that will come with product maturity.

It’s time to start thinking differently about storage and reexamining the fundamental questions and how we buy and manage storage.