Author Archive

“Live Free or Cry!”…Liberated Data Centers Don’t Cry!

Rodger Burkley

Principal Product Marketing Manager at EMC

Whether you manage a small business; regional office; mid-size enterprise, or full blown enterprise data center with regional/multi-geo sites…data of all types is exploding and costs are increasing steeply. Storage inefficiencies (from innumerable copies, snaps, back-ups and save sets); constant provisioning; data migrations and fork lift upgrades of specialized storage hardware, raw capacity and bandwidth are hemming you in and cramping your style – and data center CAPEX, OPEX and budget. Your hair’s turning white, BP’s up and your spouse or significant other (and the kids and dog/cat) seldom see you.

On top of that, you’re battling vendor lock-in, insidiously escalating shadow IT public cloud usage (and monthly fees) and growing mumbling/grumbling from your less than happy users and SLA clients.  Oh…and, yes, it’s time to go back to the well and ask for even more $$$s as you realize your recently purchased and installed storage array is getting full/utilized at around 50% or so. Time to do a SWAG on how much additional raw storage capacity you’ll be needing over the next couple years and order another sizable array upgrade….and brace yourself for some downtime and tedious data migration(s) and provisions for RAID aggregates, groups, folders and volumes.  Billy Joel’s hit song “Pressure” comes to mind!  Is there a better way to go?  Yes!

Storm Cloud

What can I say, ‘The Cloud’ can be dark and scary as far as your data security is concerned…and it can sneak up on you.

Why not liberate your data center?  Liberate your data center with vendor and hardware neutral commodity based server platforms that monetize your host application servers’ direct attached storage (DAS) for  maximum performance and flexibility.  Also enjoy in the process lower TCO and a new software defined storage architecture that yields true linear capability for compute, storage capacity and throughput.  Liberate your data center with a storage platform that gives you total elasticity to add or remove resources in response to real-world, real-time compute and storage needs with the ability to scale (on the fly, with no down time) to many Petabytes and millions of I/Os per second (IOPS).   So liberate your data center with a software-defined (SDS) server SAN…and EMC’s ScaleIO!

Incidentally, SDS server SANs are optimal for building hyper-scale private, hybrid or public clouds.  Or perfect for building hyper-performance scalable and elastic enterprise storage systems (as in millions of IOPS) for high performance applications (HPAs).  Just start with a minimum of three servers (with DAS of any media type and amount of excess raw storage capacity)…and grow to thousands of nodes with Petabyte scale capacities. Grow at your convenience and need over time – with no disruptions to your operations. Just scale-out with more servers/nodes, repurposed or purpose bought to add to your server SAN..   And scale-up with more DAS devices on those same participating servers. What could be simpler?

The beauty is you won’t miss the extensive upfront planning and justification for additional storage provisioning, forklift upgrades, data migrations, long hours and downtime involved. Just grow in small, ‘baby step’ increments by adding new Flash SSDs and HDDs to existing or new host server local storage….and even create your own storage performance ‘tiers’ (or sub-pools) to match your application or volume’s performance or resource capacity requirements.  Make adjustments to your server SAN cluster using a simple dashboards GUI to monitor system status and enter simple English commands to manage this ‘fluid’ SDS based system.  THIS is the power (and freedom) of software defined platforms. They create an abstraction layer between physical resources and logical management of operations….monitored from a ‘single pane of glass’ application-like software install right on your host server(s).

ScaleIO GUI

ScaleIO’s GUI Dashboard monitors your server SAN’s status, performance and operation in real-time — and tells you when (and how fast) it’s rebuilding data (when servers and/or DAS devices are taken off-line for MX or any reason) or auto balancing across participating host servers.  Simple CLI English language inputs adds/removes host servers and storage devices; designate Protection Domains (for multiple tenants/data partitioning); create Server Fault Sets (to increase high availability and/or scheduled MX) and so on ….. ALL ‘on the fly’ with no service disruption or “outage”….leveraging your DAS excess capacity!

How does this all work?  Simply put, a SDS server SAN system pools together disparate, isolated local storage (DAS) from participating host application servers and forms a single, aggregated virtual SAN that grows bigger and faster as you add more host servers and storage devices to it.  Non-traditional storage….that’s what we’re talking about here.  No specialized storage hardware (host bus adapters, hardware arrays, FC switches or extensive racking and thick expensive interconnect cabling need not apply).  Freedom via commodity hardware-based systems and vendor neutral/agnostic storage solutions….  Live free!

Folks, this is what’s driving hyper-converged storage solutions in the storage industry now…for block (structured data) or file data and object data (unstructured data)  storage. What about the Cloud?  Why rent when you can own….cheaply…using familiar commodity based physical or virtualized servers?  Ever look closely at somebody’s (hopefully not yours) monthly usage utility bill from Amazon Web Services, Microsoft’s Azure or Google’s public cloud?  Be prepared for sticker shock from the ‘we charge you for everything’ usage detail and escalating costs as your “user troops break ranks” and create their own shadow IT operation by subscribing to more and more Cloud services and compute and storage capacity.

And with a robust, resilient and fast performing SDS server SAN you can build your OWN private Cloud on premises….and not have to worry about data security or access when relying on the Public Cloud.

EMC’s ScaleIO is an example of “a robust, resilient and fast performing SDS server SAN.”  OK…so I work at EMC.  Just search for “ScaleIO” on the web and you’ll see what I mean.  YouTube videos walk you through this new technology, architecture and SDS product platform too.  If for no other reason, get up to date on this newest emerging technology that is truly liberating data centers with software based, hyper-converged (all application, CPU, networking and storage functions/resources in one HW platform…or “node”) infrastructure.  Skeptical?  Why not try ScaleIO yourself with EMC’s free and frictionless ScaleIO download. Just like that memorable TV ad a few decades back…”Try it, you’ll like it.”…

Sure, other vendors out there are offering similar SDS product solutions…either via pure software only licensing (usually capacity based) or a pre-packaged/bundled “hyper-converged storage appliance” or both forms. ScaleIO is sold in both forms….software or appliance…and that gives you more flexibility as both formats serve their purposes.  You might also have heard about Ceph and “ICE” (Inktank’s Ceph Enterprises distributed commercially by RedHat).   But when you look at ScaleIO’s inherent high performance, ability to scale from 12TB to 16PB raw capacity, dynamic elasticity and flexibility to add or remove nodes, storage devices and servers without any disruption to operations and other quality of service (QoS) features/functionality ScaleIO brings to your datacenter rack(s)….nothing out there comes close.  Bold statement?  Indeed.  But as they say, “an informed buyer is an educated and confident buyer…” 🙂 (OK…I took some liberties with that saying for sure.)

Does this mean the end to “traditional storage platforms” as we know and (mostly) love them today?  No.  Not hardly.  There will always be a need, use and place for traditional SAN (block), NAS (file) and archival (object/cloud) storage platform products.

The challenge, of course, is in identifying and rationalizing respective use cases, assimilating new technology/architectures and integrating ‘the new and old’ into seamless, efficient deployments that leverage (and monetize) each other’s strengths, specialized features/capabilities and value add that fit YOUR data center and IT needs.   With the storage industry leader like EMC, you’ll be getting all the advice, support, products and solutions (across the entire storage spectrum) to help you take advantage of both newer and traditional storage technologies and value propositions.

In closing, this was definitely an unabashed paid endorsement for EMC’s ScaleIO.  But more importantly, hopefully this post highlights just how much these new SDS server SANs in general are changing the datacenter landscape and freeing IT/MIS CIOs, directors, admins and managers from hardware and vendor lock-in and older, more traditional storage architectures.  It’s happening as you read this….

Want to know more?  Check out @EMCScaleIO on Twitter!   Get on board the emerging storage technology and ScaleIO train.  Live Free…and Don’t Cry!

In Cyber Space No One Can Hear You Scream

Rodger Burkley

Principal Product Marketing Manager at EMC

No doubt you fans of sci-fi and “vintage feature films” out there instantly recognize this famous (and hauntingly memorable) movie tagline.  Hint:  For those of you who regard Hollywood movies and horror futuristic science fiction as being alien to your “core” interests or even remote curiosity…

Yes, “Alien” was a ground breaking, Cyber Space Screammemorable sci-fi horror flick directed by Ridley Scott.
First released in 1979, it was a trend setter for sure… and one that launched a whole bevy of Aliens.  It changed everything in terms of high action, high thrills (and scares) science fiction drama flicks.  Of course, I first saw it much later on VHS when I was old enough to watch it without having nightmares… (at least that’s my story and I’m sticking to it…)

And — yes — in the vacuum of outer space sound doesn’t propagate or travel…so indeed no one can hear you scream. Turns out, no one can hear you scream in cyber space either… particularly where the Public Cloud is involved.

As good as the Public Cloud and various service providers are, the simple fact is that you lose control of your storage and compute resources once you get on the Cloud wagon.  More importantly, you lose control and access of your valuable data once you upload it onto some Public Cloud service provider’s infrastructure.

Need some ‘fact checking’ validation here?  Amazon Web Services (AWS) is the biggest Public Cloud service provider, followed by Microsoft Azure, Google Cloud Platform and a number of others.  It’s been a tough week for AWS customers.  They’ve had two service outages last week alone!  The dreaded ‘D word’ in IT….Downtime!  The silver lining?  Well, at least AWS customers’ monthly usage service fees will be lower this month… (more…)

ScaleIO: When More is Better…and Less is More!

Rodger Burkley

Principal Product Marketing Manager at EMC

By now, you’ve no doubt heard how Software Defined Storage (SDS) and hyper-converged server SANs are reshaping the storage industry (and use case) landscape.  Market acceptance continues to grow at an accelerated pace.  There are now many established and new vendors offering hyper-converged storage appliances and SDS systems.   EMC’s own ScaleIO SDS platform continues to score mounting recognition, kudos and accolades with our growing list of customers.Hyperconverged  ScaleIO has even won-over storage techies and IT Management who were initially skeptical that ScaleIO would actually completely deliver on its value proposition and capabilities.

Why all the buzz and hype?  Customers – and the IT datacenter and storage market — get it and are embracing this new, “disruptive” technology by introducing it to their enterprise data centers or using it to create hyper-scalable virtualized infrastructures for cloud applications.  The promise and appeal of installing software on individual commodity host application servers to create a virtual storage pool (i.e., “server SAN”) from each participating server’s excess direct attached storage (DAS) without requiring additional specialized storage/fabric hardware is alluring…and almost too good to be true.  High Availability, commodity based hardware, linear performance and storage capacity scalability, “SAN-less” data storage, lower TCO, elasticity and flexibility are just a few compelling arguments in favor of hyper-converged architectures in general and SDS system in particular. (more…)

Software-Defined Storage Marries Enterprise Storage with the Cloud

Rodger Burkley

Principal Product Marketing Manager at EMC

This blog focuses on software defined storage….the all caps version.   SDS.  Or….by another popular industry term….the Software Defined Data Center (SDDC) platform.  SDDC platforms are transforming Data Centers because theySoftware Storage can simultaneously marry (ah…some might say integrate) a variety of traditional hardware storage resources, data types and technologies into one “federated” and aggregated data center infrastructure.   Moreover, SDDC platforms can control, manage and even monitor the entire data center storage (and compute and networking) operation from a “single pane of glass” console – outside the data path.  Yes, I’m referring to ViPR Controller SDS.

ScaleIO is an excellent commodity hardware based software defined storage (sds) system for creating block data Server SANs.  It’s hyper-converged, hyper-scalable, flexible and highly elastic.  In fact, by its very name creates a scalable low-cost virtual SAN array from commodity servers.

As good as ScaleIO (sds) is, however, it’s not the whole SDS story.  A good piece to be sure.  But it’s a virtual SAN solution that covers a portion of today’s contemporary enterprise data center’s needs.    True, ScaleIO can completely cover some specific storage use cases extremely well and efficiently.   Fact is, our competitors out there – particularly from the Server SAN appliance camp – may be overstating the extent Server SANs and “SAN-less” storage can be integrated with SMB and Enterprise Data Centers’ existing traditional storage infrastructure and arrays.  In fact, many customers confuse ScaleIO (or VSAN) sds with ViPR Controller SDS. After all, they’re both software defined, right?

Many of you already know this.  The principle cause for some of this confusion is that traditional external storage is quite alive and doing well in today’s storage market environment and Enterprise customer base.  Most of these enterprises store the vast majority of data on their traditional hardware arrays.  Fact is, they’ll probably be doing so for a long time.  Just witness the “demise of tape” as a deep, ‘frozen’ archive medium.  And according to IDC, more than 20,000 petabytes of new external storage system capacity was purchased in 2013 alone.

So rumors of traditional external storage’s impending death are a bit exaggerated…to rip off a humorist slogan from one humorous wise old sage. Accordingly, it stands to reason that a SDS federated and unified management platform solution needs to work seamless with that traditional hardware resource layer…comprised of multiple vendors…and data types.  And ViPR Controller does that….hands down.

On the other end of the data center spectrum…or relay station… however, is the need to manage external data storage resources and I/O traffic access that lie physically outside the data center’s local physical or logical resource control.   Specifically, the Cloud – whether it be Public or Enterprise Off-premise…

When it comes to Public Clouds, service providers like Amazon, Google and Microsoft will remain big players due to their sheer economies of scale and easy table stakes entry.  You hear a lot lately about ‘supplemental storage’ or remote DR/copy on these Public Clouds.  But those very same Public Clouds concern many Enterprise IT Directors too…. (i.e., service outages, SLAs, data security/integrity, multi-tenancy, etc.).   Not surprisingly, Private and Hybrid ‘on-premise’ Clouds are gaining increased popularity and momentum.  So a true, useful/attractive “federating” SDS platform needs to support, manage and control traditional external storage; Cloud storage and – yes – commodity based sds Server SAN arrays like ScaleIO and VSAN.

Bottom-line?  Viable and highly productive/ROI software defined storage implementations should not be limited to lower case sds and/or strictly commodity hardware.  With ViPR Controller and it’s unifying software abstraction layer, a broad platform can be created for managing, provisioning and automating federated storage that includes traditional enterprise storage platforms as well as the “Cloudsphere”, Server SANs, Data Lakes, OpenStack, REST APIs, on-line analytics and other data center resources, tools and access portals.  Again, ViPR Controller shines as a true SDS/SDDC (or whatever the latest popular term happens to be).

Obviously, implementing a purpose-built sds (i.e., ScaleIO) or SDS (i.e,. ViPR Controller or ECS) in an Enterprise Data Center needs to be well thought-out and phased in incrementally.  Why?  Storage systems invariably represent an Enterprise Data Center’s largest investment – and arrays typically have long operational life cycles.  Plus storage admins are used to and quite familiar with them.  This is their bread and butter and ‘job security’.  And use cases involving evolving Public, Hybrid or Private on or off premise storage clouds – married with legacy on-premise, metro or remote geo based traditional storage —  must also be well considered when  proposing and evaluating software defined storage at any level.

In closing, users don’t like to manage multiple storage stacks, architectures or interfaces.  Simplicity and easy everything are highly valued.   It’s all about delivering broad enough, all-encompassing storage strategies that help SMB and Enterprise customers get the most out of their current investments/ROI while adopting and/or migrating to new, next-gen storage technologies in an orderly, seamless and painless manner.  Did I mention ViPR controller and “marriage”?  Maybe more like the “Presiding Official”…

Sizing up Software Defined Storage

Rodger Burkley

Principal Product Marketing Manager at EMC

By now, you’ve all heard how Software Defined Storage (SDS) is reshaping the storage industry (and use case) landscape. The market gets it and increasingly users are embracing this new, “disruptive” technology by introducing it to their enterprise data centers or using it to create hyper-scalable virtualized infrastructures for cloud applications. After all, the appeal of installing software on individual commodity host application servers to create a virtual storage pool (i.e., “server SAN”) from each participating server’s excess direct attached storage (DAS) without requiring additional specialized storage/fabric hardware is alluring…and almost too good to be true.

Throw in the added synergy and side benefits like ‘on-the-fly’ elasticity; linear I/O processing performance capacity scalability; simplicity and ease of use; hardware/vendor agnosticism and unparalleled storage platform flexibility and you might think “SDS server SAN” technology can solve world hunger too. Well, if not world hunger, perhaps today’s contemporary data centers’ thirst for a simpler, less expensive higher performing and more flexible storage solution for block and/or object….

Yes. There’s a lot of excitement, market activity and hype out there around SDS and Server SANs in general. But don’t take my word for it. Though data compilations for CY 2014 aren’t available yet, Wikibon’s market TAM and SAM sizings for 2013 are revealing.

Figure 1. Hyperscale vs Enterprise
Hyperscale vs Enterprise

Figure 2.  Vendor SOM (share of market)
Vendor

Figure one shows that (at least for 2013) the application of “Hyperscale” Server SAN’s (i.e., Petabyte Scale) generated far greater revenue than “Enterprise” Server Server SAN’s.  Why?  New VSI (Virtual Server Infrastructure) and Cloud use cases are ideally suited for the hyper-converged, hyper-scalability attributes SDS Server SAN’s bring to the table.  This is, in fact, a primary targeted use case for ScaleIO.  Why are Enterprise Server SAN’s a lot less than Hyperscale Server SANs?  This is the domain of the mission critical apps, databases and use cases that keeps IT Datacenter Directors and Administrations busy….and up at night.  It’s also the domain of traditional storage arrays and the Storage Admins, with lots of proprietary equipment (and bias) for vendors like EMC and our esteemed competitors.   These folks are wary and cautious when it comes to new technologies.  They’re not enthusiastic early adopters.   But as new technology and products mature and prove themselves, they end up being embraced by IT data center departments.  “Show me your value prop” or …”Show me the money.”  And simple, less complex storage solutions will get you in the door.  Growth is expected to be high in this hardware ‘open’ and ‘liberated’ segment over time.

Figure 2 shows the major players in the Server SAN arena.  Note that VMware’s SOM is tiny…but this is because VMware’s Virtual SAN (VSAN) wasn’t fully rolled out in the market place.   But also note the number of players.  Big players and small unknowns alike.  All vying for the coveted Enterprise Server SAN market, which is poised for growth along with the SMB and ROBO segments.

By now, you’re ready to call me out on my liberal use of SDS and Server SANs terminology.  After all, figure 2 lists hyper-converged Server SAN hardware appliance vendors (like Nutanix & Simplivity) along with pure software SDS vendors and products (like Scality, ScaleIO, Scale Computing, etc.).  So what gives?  (more…)

Hard or Soft Storage? That is the Question and the Answer

Rodger Burkley

Principal Product Marketing Manager at EMC

There’s lots of press these days on Software-Defined Storage (SDS), Software-Defined Data Centers (SDDC), Server SAN’s, software-only virtual SANs, hyper-converged storage servers, storage appliances and the like. We’ve all been inundated with this new technology and architectural terms by bloggers, marketing mavens, PR, tradeshow signage, consultants, analysts, technology pundits and CEOs of new start-ups. As a blogger and marketing guy, I plead doubly guilty. But the emergence of SDS systems and SDDCs is real and timely. Definitions and differences, however, can be a tiny bit murky and confusing.

This enabling technology is coming to market just in time as today’s modern data centers, servers, storage arrays and even network/comm fabrics are getting more and more overtaxed and saturated with mega-scale data I/O transfers and operations of all types with all kind of data formats (i.e., file, object, HDFS, block, S3, etc.). When you add in the line of business commitments for SLA adherence, data security/integrity, compliance, TCO, upgrades, migrations, control/management, provisioning and the raw growth in data volume (growing by at least 50% a year) IT directors and administrators are getting prolonged headaches.

Against this backdrop, it’s no wonder that lately I’m getting asked a lot to clarify the difference between converged storage appliances, hyper-converged/hyper scale-out storage server clusters, and pure software-defined storage systems. So I wanted to make an attempt to provide a high level distinction between a storage hardware appliance and pure software-defined (i.e., shrink wrapped software) storage system, while also providing some considerations of choosing one over the other. In fact, architectural and functional differences are somewhat blurred. So it’s mostly about packaging…but not entirely.

Basically, we all know that everything runs on software – whether it comes pre-packaged in a hardware box (i.e., appliance) or decoupled as a pure software install. There are also distinctions being made between convergence (i.e., converged infrastructure) and hyper-convergence. Convergence refers to the extent compute, storage and networking resources have been “converged” into one virtual layer or appliance box.

Regardless of whether we’re talking about a converged or hyper-converged storage appliance based system using proprietary or COTS hardware, advanced/intelligent software is required in any box to run, monitor, control and optimize the resulting storage system. Some storage appliance vendors – including EMC – offer their “secret sauce,” software unbundled in a pure, software only version like ScaleIO and ViPR 2.0; Red Hat’s ICE (Inktank Ceph Enterprise) or VMware’s Virtual SAN. The main difference between hardware storage appliances and a pure software-defined storage system is chiefly how each is packaged or bundled (or not) with hardware. Some appliances may have proprietary hardware, but not all have to, and likewise not all appliances are commodity hardware based.

A hyper-converged box is typically a commodity based hardware appliance that has all three computing resource functions rolled up in one box or single layer. Traditional arrays consist of three separate layers or distinct functional components. Some commodity server based pure software-defined storage systems are also hyper-converged in that they are installed on application server hardware. Other converged systems (typically appliances) may consist of storage and networking in a commodity or proprietary box – for two layers. Converged and hyper-converged appliances and SDS systems, however, all typically aggregate pooled storage into one shared clustered system with distributed data/protection spread across appliance boxes or host servers/nodes. They tend to be storage device/hardware agnostic as well, supporting PCIe I/O and SSD flash media as well as traditional HDDs.

Appliance based solutions offer plug-n-play boxes with predictable scalability which can be quickly added for scale-out (more nodes) or scale-up (more storage capacity). Local area clusters can be created with data protection spread across multiple shared appliance boxes. Flash caching or storage pooling/tiering performance features enhance the overall user experience. Adding additional storage and compute resources is predictable in terms of incremental CAPEX outlays. There may be some constraints on scalability, performance, and elasticity capabilities but these restrictions may not be deal breakers for some use cases. ROBO, retail store outlets, SMBs and smaller datacenters, for example, come to mind where smaller capacity, defined hardware storage server appliances provide adequate converged resources. “Datacenter in a box” is often used by some appliance venders to position these smaller, geographically distributed deployments. It’s an apt sound byte. Other larger customers might simply add another box for more symmetrical storage, I/O performance, or compute. Either way, they get it all in a single unit.

hardorsoft2
In other cases, a pure software-defined storage solution or software-defined data center can be better. Why? Well again, use cases are a big driver. Optimal use cases for these commodity hardware based SDS systems include database/OLTP, Test/Dev, Virtualization and Big Data/Cloud computing, and where availability of existing commodity server resources for lower cost scalability is high. SDS systems like ScaleIO can be installed on commodity application servers and pool server DAS together to form a converged, aggregated shared storage asymmetric cluster pool with distributed data protection across participating servers. They do this while delivering huge performance (IOPS and bandwidth) and scale-out synergies realized from parallel I/O processing. In essence, a peer-to-peer grid or fabric is created from this software. Blogademically speaking, an SDS is analogous to an unconstrained system versus a contained appliance based solution. It goes without saying that both have their strong points.

Another aspect that comes into play is your tolerance for installation, integration, and deployment activities. Both hardware appliances and SDS systems have their strong and weak points in terms of the degree of expertise needed to get up and running. SDS systems can make that task set easier with their thin provisioned software module/installs, intuitive monitoring dashboard GUIs and/or English language based command interfaces. Thin provisioning available on appliances and some SDS systems offers more efficiency where the amount of resource used is much less than provisioned. This enables greater on-the-fly elasticity for adding and removing storage resources, creating snap shots as well as leveraging storage and resource costs in a virtual environment.

For some users, a commodity based converged or hyper-converged hardware appliance with internal hybrid storage (i.e., SSD Flash and HDDs) is the way to go. For others, it’s a pure SDS solution. Some customers and data center administrators favor a bundled, pre-packaged hardware appliance solution from vendors. They offer predictable resource expansion, performance and scalability as well as quick set-up and integration. A growing segment, however, prefers the ease of install: greater on-the-fly elasticity, lower TCO, hyper scale-out capacity/performance by simply adding more servers and DAS devices and reduced management overhead of an SDS solution. Thin provisioning allows space to be easily allocated to servers and on a just-enough and just-in-time basis for ease of scalability and elasticity.

In the end, the question of going hard or soft for converged or hyper-converged storage systems depends on your data I/O requirements, use cases, goals/objectives, existing resources and environment(s) and plans for future expansion, performance and flexibility. Both have utility.

Categories

Archives

Connect with us on Twitter