Inside System Storage -- by Tony Pearson

Next week, I suspect some of the kids on my block will be playing with radio-controlled cars orplanes. If you are not familiar with these, here's a [video on BoingBoing]that shows Carl Rankin's flying machines that he made out of household materials.

Which brings me to the thought of scalability. For the most part, the physics involvedwith cars, planes, trains or sailboats apply at the toy-size level as well as the real-world level. One human operator can drive/manage/sail one vehicle. While I have seen a chess master play seven opponents on seven chess boards concurrently, itwould be difficult for a single person to fly seven radio-controlled airplanes at the same time.

How can this concept be extended to IT administrators in the data center? They have to deal withhundreds of applications running on thousands of distributed servers.In a whitepaper titled [Single System Image (SSI)], the threeauthors write:

A single system image (SSI) is the property of a systemthat hides the heterogeneous and distributed nature of theavailable resources and presents them to users and applicationsas a single unified computing resource.

Server clusters

Even in the case where yourvehicle is being pulled by eight horses--(or eight reindeer?)--a single operator can manage it, holding the reins in both hands. In the same manner,IBM has spent a lot of investment and research into supercomputers, where hundreds of individualservers all work together towards a common task. The operator submits a math problem, for example,and the "system system image" takes care of the rest, dividing the work up into smaller chunksthat are executed on each machine.

When done with IBM mainframes, it is called a Parallel Sysplex. The world's largest business workloadsare processed by mainframes, and connecting several together and working in concert makes this possible.In this case, the tasks are typically just single transactions, no need to divide them up further, justbalance the workload across the various machines, with shared access to a common database and storageinfrastructure so they can all do the work equally.

Last August, in my post [Fundamental Changes for Green Data Centers], I mentioned that IBM consolidated 3900 Intel-based servers onto 33 mainframes. This not only saves lots of electricity, but makes it much easier for the IT administratorsto manage the environment.

Storage virtualization

Parallel Sysplex configurations often require thousands of disk volumes, which would have been quitea headache dealing with them individually. With DFSMS, IBM was able to create "storage groups" wherea few groups held the data. You might have reasons to separate some data from others, put them inseparate groups. An IT administrator could handle a handful of storage groups much easier than thousandsof disk volumes. As businesses grow, there would be more data in each storage group, but the numberof storage groups remains flat, so an IT administrator could manage the growth easily.

IBM System Storage SAN Volume Controller (SVC) is able to accomplish this for other distributed systems.All of the physical disk space assigned to an SVC cluster is placed into a handful of "managed diskgroups". As the system grows in capacity, more space is added to each managed disk group, but few IT administrators can continue to manage this easily.

The new IBM System Storage Virtual File Manager (VFM) is able to aggregate file systems into one globalname space, again simplifying heterogeneous resources into a single system image. End users have a singledrive letter or mount point to deal with, rather than many to connect to all the disparate systems.

Centralized Administration

Lastly we get to the actual management aspect of it all. Wouldn't it be nice if your entire data centercould be managed by a hand-held device with two joysticks and a couple of buttons? We're not quite there yet, but last October we announced the [IBM System Storage Productivity Center (SSPC)]. This is a master consolethat has a variety of software pre-installed to manage your IBM and non-IBM storage hardware, includingSAN fabric gear, disk arrays and even tape libraries. It lets the storage admin see the entire data centeras a single system image, displaying the topology in graphical view that can be drilled down using semanticzooming to look at or manage a particular device or component.

Customers are growing their storage capacity on average 60 percent per year. They could do this by havingmore and more things to deal with, and gripe about the complexity, or they can try to grow theirsingle system image bigger, with interfaces and technologies that allow the existing IT staff to manage.

technorati tags: Winter solstice, Golden Compass, Richard Dawkins, radio-controlled, cars, planes, trains, sailboats, automobiles, IBM, mainframe, system z, parallel sysplex, single system image, DFSMS, SAN Volume Controller, SVC, Virtual File Manager, VFM, System Storage, Productivity Center, SSPC, master console, SAN, fabric, gear, disk, tape, libraries, data center, topology, semantic zooming

The [Robert Frances Group] have put out a research paper titled Optimizing Data Retention and Archiving - November 2007 that helps IT executives understand the cost differences for a disk-only archive approach versus disk/tape archive approach and how an [IBM System Storage DR550] offering can help address the long-term storage archive requirements with a world-class storage strategy that reduces cost, improves efficiency and supports compliance. Here is an excerpt:

Ongoing legal, audit, and regulatory requirementswill continue to drive IT groups to improvearchive policies, processes, strategy, andefficiency. The choice of which technologies touse will have a profound impact on the success ofsuch efforts, since technologies like the DR550embody many aspects of the strategy, processes,and policies that must be decided upon. When itcomes to tape, IBM's DR550 is unique inproviding that support. Competitors tout disk-onlysolutions as the wave of the future, but researchindicates otherwise. The most basic benefits arecost and mobility, and despite the various vendorproclamations to the contrary, tape is still only afraction of the cost of disk and will remain so inthe foreseeable future.

This paper is yet another nail in the coffin of EMC Centera.In his post [Anyone Naughty on Your List…], Jon W Toigo points to an eBay fire sale of an EMC Centera Gen 4.

There has never been a better time to switch from EMC Centera to theIBM System Storage DR550.

technorati tags: Robert Francis Group, IBM, DR550, archive, data retention, storage, solution, disk, tape, drunkendata, Jon Toigo, EMC, Centera

Why now?

This is a reasonable question. Since Invista 2.0 came out months ago in August, and Invista 2.1 is rumored to be out by end of this month, why put out a press release now, rather than just wait a few weeks? Thesignificant part of this announcement was that EMC finally has their first customer reference.To be fair, getting a customer to agree to be a reference is difficult for any vendor. Some non-profitsand government agencies have rules against it, and some corporations just don't want to be bothered byjournalists, or take phone calls from other prospective customers. I suspect EMC wanted to put the good folks from Purdue University in front of the cameras and microphones before they:

• suffer an outage,
• change their minds, and/or
• leave for Winter break

It takes a while for new technologies to get adopted by the marketplace. Geoffrey Moore wrote a book titled [Crossing the Chasm: Marketing and Selling Disruptive Products to Mainstream Customers] that I highly recommend. If you don'thave time to read the entire book, here is a quick [11-page summary] from Parkerhill Technology Group.

In Moore's terminology, Purdue University would be a "technology enthusiast", interested in exploring the technologyof the EMC Invista. Universities by their very nature often see themselves as early adopters, willing to take big risks in hopes to reap big rewards. The chasm happens later, when there are a lot of early adopters, all willing to be reference accounts. The mainstream market--shown here as pragmatists, conservatives, and skeptics-- are unwillingto accept reference claims from early adopters, searching instead for moderate gains from minimal risks. They prefer references from customers that are similar in size and industry. Whether a vendor can get a product to cross this chasm is the focus of the book.

Why "SAN" virtualization?

Technically, Invista is "storage" virtualization, not "SAN" virtualization. Virtualizationis any technology that makes one set of resources look and feel like a different setof resources, preferably with more desirable characteristics. You can virtualizeservers, SANs, and storage resources.

Here's a quote from Cisco's whitepaper called [Storage Virtualization a Work in Progress]

Virtual SAN (VSAN) technology, supported bythe Cisco MDS 9500 Series Multilayer Director Switch, partitions a single physical SAN into multipleVSANs, allowing different business functions and requirements to share a common physical infrastructure.

How does Invista advance Cisco's VSAN functionality? It doesn't, but that doesn't makethe title a falsehood, or the press release by association full of lies.If you read the entire press release, EMCcorrectly states that Invista is "storage" virtualization. Some storagevirtualization products, like EMC Invista and IBM System Storage SAN Volume Controller (SVC), require a SAN as a platform for which to perform their magic.Marketing people might use the term "SAN" torefer not just the network gear that provides the plumbing, but also to include the storage devices that are attached to the SAN. In that light, theuse of "SAN virtualization" can be understood in the title.

More importantly, it appears that EMC no longer requires that you purchase new SAN equipment from themwith Invista. When the Invista first came out, it cost over a quarter-million US dollars to cover thecost of the intelligent switches, but with the price drop to $100K, I imagine this means theyassume everyone has an appropriately-supported intelligent switch already deployed.

Why this architecture?

In his post [Storage Virtualization and Invista 2.0], EMC blogger ChuckH does a fair job explaining why EMC went in this direction for Invista, and how it is different thanother storage virtualization products.

Most storage virtualization products are cache-based. The world's first disk storagevirtualization product, the IBM 3850 Mass Storage System, introduced in 1974, and thefirst tape virtualization product, the IBM 3494 Virtual tape Server, introduced in 1997, bothused disk cache in front of tape storage. Later virtualization products, like IBM SVC and HDS USP-V, use DRAM memory cache in front of disk storage, but the concept is the same.People are comfortable with cache-based solutions, because the technology is matureand well proven in the marketplace, and excited and delighted that these can offer the following features in a mixed heterogeneous disk environment:

• improved performance
• instantaneous point-in-time copy
• synchronous mirroring
• asynchronous mirroring

None of these features are provided by Invista, as there is no cache in the switch. Instead,Invista is a "packet cracker"; it cracks open each FCP packet, inspects and modifies the contents, then passes theFCP packet along to the appropriate storage device. This process slows down each read andwrite by some amount, perhaps 20 microseconds. The disadvantage of slowing down every readand write is offset by having other benefits, like non-disruptive data migration.

To compensate for Invista's inability to provide these features,EMC offers a second solution called EMC RecoverPoint, which is an in-band cache-based appliancesimilar in design to SVC, but maps all virtual disks one-to-one to physical disks. It offersremote distance asynchronous mirroring between heterogeneous devices.EMC supports RecoverPoint in front of Invista, but if you are considering buying bothto get the combined set of features, you might as well buy an IBM SVC or HDS USP-V instead,in one system, rather than two, which is much less complicated. IBM SVC and HDS USP-Vhave both "crossed the chasm" having sold thousands of units to every type and size of customer.

technorati tags: EMC, Invista, SAN, virtualization, storage, disk, systems, IBM, BarryW, Purdue, University, Geoffrey Moore, chasm, Cisco, VSAN, SAN Volume Controller, SVC, HDS, USP-V, RecoverPoint

Last year, I covered Chris Anderson's book [The Long Tail]. This year, Chris Anderson, editor-in-chief of Wired.com, has an upcoming book titled Free, the past and future of a radical price. Chris talked about his book here at Nokia World 2007 conference, and the [46-minute video] is worth watching.He asks the big question "What if certain resources were free?" This could be electricity, bandwidth, or storage capacity. He explores how this changes the world, and createsopportunities for new business models. However, many people are stuck in a "scarcity" modeland treat nearly-free resources as expensive, and find themselves doing traditional things thatdon't work anymore. Chris mentions [Second Life] as aneconomy where many resources are free, and seeing how people respond to that.Rather than focusing on making money, new businesses are focused on gainingattention and building their reputation. Here are some example business models:

• Cross-subsidy: give away the razors, sell the razor blades; or give away cell phones and sell minutes
• Ad-Supported: magazines and newspapers sell for less than production costs
• Freemium: 99% use the free version, but a handful pay extra for something more
• Digital economics: give away digital music to promote concert tours
• Free-sample marketing: give away samples to get word-of-mouth advertising
• Gift economy: give people an opportunity and platform to contribute like Wikipedia

Nick Carr writes a post [Dominating the Cloud], indicatingthat IBM, Google, Microsoft, Yahoo and Amazon are the five computing giants to watch, as they are more efficient atconverting electricity into computing than anyone else. Last month, I mentioned IBM and Google partnership on cloud computing in my post[Innovationthat matters: cell phones and cloud computing].Nick's upcoming book titled[The Big Switch] looks into "Utility Computing",comparing the change of companies generating their own electricity to using an electric grid, to the recent developments of cloud computing and software as a service (SaaS). Amazon's latest "SimpleDB" online databaseis cited as an example.

Last, but not least, Seth Godin writes in his post [Meatballs and Permeability] about the bits-vs-atoms issue, what Chris Anderson above refers to as the new digital economy. The idea here is that value carried electronically as bits (digital documents, for example) have completely different economics than value carried as atoms (physical objects), andrequires new marketing techniques. Methods from traditional marketing will not be effective in this new age.Here is a [review] of Seth's new book Meatball Sundae: Is Your Marketing Out of Sync?

All three of these books seem to be covering the same phenomenon, just from different viewpoints. I lookforward to reading them.

technorati tags: Long Tail, Chris Anderson, Wired, Nokia World, secondlife, cross-subsidy, digital economy, Nick Carr, Big Switch, utility computing, IBM, Google, Microsoft, Yahoo, Amazon, SimpleDB, Seth Godin, Meatball Sundae, bits, atoms