The document discusses SimpliVity's OmniCube hyperconverged infrastructure platform. It aims to provide both cloud economics and enterprise capabilities like data protection, efficiency, performance and unified management. SimpliVity's key innovation is its data virtualization platform which performs real-time deduplication, compression and optimization of data without impacting performance. This allows data to be optimized once and accessed globally. The OmniCube combines compute, storage, networking and management into an integrated 2U building block to simplify IT infrastructure management and costs compared to traditional legacy stacks.
Cloud Economics with Enterprise Protection and Performance
1. Abstract
SimpliVity OmniCube is the only hyperconverged infrastructure platform that combines x86
Cloud Economics without Compromising Enterprise capabilities: Data Protection, Data Efficiency;
Performance and Global Unified Management.
SimpliVity’s Data Virtualization Platform is the key to Simplifying IT. A novel global data
architecture.
August 2014
Overview of SimpliVity’s OmniCube:
Cloud Economics with Enterprise Performance,
Protection and Functionality
2. Contents
1. SimpliVity Company Overview .............................................................................................................. 3
2. The Data Problem ................................................................................................................................. 4
3. The Legacy Stack Does Not Solve the Data Problem ............................................................................ 7
4. IT Is Turning To the Cloud ..................................................................................................................... 8
5. SimpliVity OmniCube Solves the Data Problem .................................................................................. 10
6. SimpliVity’s Three Core Innovations ................................................................................................... 11
7. Data Virtualization Platform ............................................................................................................... 14
7.1 Technology Overview ........................................................................................................................ 14
7.2 Deduplication, Compression, and Optimization Today .................................................................... 15
7.3 SimpliVity Data Virtualization Platform ............................................................................................ 15
7.3.1 The Starting Point: Real-time Deduplication, Compression and Optimization without Impact to
Performance ....................................................................................................................................... 16
7.3.2 OmniCube Accelerator Card ....................................................................................................... 17
7.3.3 Enhancing the Value through Optimization................................................................................ 17
8. Global Federated Management .......................................................................................................... 18
9. Path to Hyper Convergence (v 3.0) ..................................................................................................... 19
10. Summary ......................................................................................................................................... 22
4. 1. SimpliVity Company Overview
SimpliVity was founded in 2009 with a mission to simplify IT.
Specifically, SimpliVity’s intentions has been to deliver to customers the best of both worlds:
x x86 Cloud Economics
x Enterprise functionality, protection and performance
These dual goals required three and a half years of development in stealth before OmniCube was made
generally available in April 2013, given that core technologies could not be added after the fact.
Figure 1 - SimpliVity Overview
SimpiVity’s go-to-market is 100% through the channel. On July 1st, SimpliVity formally announced the
SimpliVity ParterAdvantage Program underscoring the priority and focus that SimpliVity devotes to its
world-class partners.
SimpliVity has raised a total of $101M in three rounds of funding by top-tier venture capital firms including
Accel Partners, Charles River Ventures, DFJ, Kleiner Perkins Caufield & Byers (KPCB) Growth and Meritech
Capital Partners. These venture firms backed successful companies such as Amazon, Google, Facebook, and
others.
Since launching the first product – OmniCube – in early 2013, SimpliVity has experienced rapid customer
adoption and world-class channel development.
We already have hundreds of customers deployed in production and hundreds of channel partners globally,
and we’ve won awards that are more typical of larger companies, such as VMworld Gold in 2013 for best
product in storage and backup.
5. Figure 2 illustrates our view whereby what Enterprise customers need is more than what cloud companies or
web companies deliver. Enterprise customers need more functionality, protection and performance than is
currently delivered at or by the Web companies. Enterprise customers want the best of both worlds: x86
Cloud economics, with Enterprise functionality, protection and performance.
Figure 2: Can Facebook and Google offer everything?
2. The Data Problem
IT organizations are asked by their business constituents to maintain service level agreements and
provide new innovation, while budgets remain flat. It’s the proverbial “do more with less.”
Not only is data growing exponentially – to 40 zettabytes by 2020, according to IDC – but we must do
more with this data than ever before:
x Ensure high performance for mission-critical applications.
x Provide mobility across data centers and remote offices.
x Integrate data protection.
x Offer streamlined management to reduce operational expense.
These growing demands, and the simultaneous business goals to reduce cost and increase agility and
flexibility have led IT organization to quickly move towards both virtualization and the cloud.
“Virtualization is the new default in the data center, with more virtual than physical servers today.”1
According to research conducted by Vanson Bourne, IT organizations, on average, expect 59% of their
1 IDC. “Worldwide Cloud and Virtualization System Software, 2013.” Dec. 2013. Presentation.
6. server workloads to be virtualized2 and Gartner supports it by saying: “almost two-thirds of x86
architecture workloads have been virtualized on servers”.3
Virtualization starts to solve the problem at the server level. But IT organizations still handcuffed by the
Data Problem.
Figure 3 – A Picture of Today’s Data Center
A snapshot of today’s IT environment is one of complexity, cost and inflexibility that inhibit IT staff from
effectively supporting the business. Several challenges are listed below and are illustrated in Figure 4.
1. Inability to Innovate: An estimated 70% of the time, IT employees are just “keeping the lights on”
by conducting maintenance, upgrades, patches, etc., and only 30% are they building new
innovation or engaging in new projects that will push the business forward.
2. Complexity and Decreasing Employee Productivity: The typical datacenter faces the complex
challenges of assimilating many different IT stacks, including primary storage, servers, backup
deduplication appliances, WAN optimization appliances, SSD acceleration arrays, public cloud
gateways, backup applications, replication applications, and other special purpose appliances and
software applications. IT staff must somehow cobble them together but it inevitably results in poor
utilization, idle resources, and high labor costs.
3. Multiple points of management: Many modern infrastructures require dedicated staff with
specialized training to manage the interface of each stand-alone appliance.
2 http://www.zdnet.com/virtualizing-the-enterprise-an-overview-7000018110/
3 Gartner. “Magic Quadrant for x86 Server Virtualization Infrastructure.” June 2013.
7. 4. Limited data mobility: As organization move to virtualization, they are presented with the benefits
of VM mobility. VMs can be shifted from server to server or data center to data center using tools
like VMware vMotion. But, in today’s IT infrastructure, the data associated with the VM is still
limited in its mobility.
5. Inflexible Scaling up and down: Predicting infrastructure requirements three years into the future
is not practical or efficient. Datacenter managers need a solution that can scale out with growing
demand without increased complexity. Similarly, the ability to quickly scale down infrastructure or
rebalance workloads is time consuming and difficult.
6. Poor IT and Business Agility: The complexities of legacy infrastructure place a burden on IT teams
in day to day management. The inherent inflexible nature of these technologies also burden IT
teams, and therefore the business, in their ability to quickly roll out new applications or build new
capabilities that that the business requires. More technically, there are also restrictions on legacy
infrastructure ability to restore, replicate, and clone data both locally and to remote datacenters in
an efficient manner at scale. This introduces economical limitations in terms of sought data
management and protection practices.
7. Cost: Highly functional and high performance data storage is dependent on an expensive stack of
technologies from storage area network (SAN) or Network Attached Storage (NAS), to target
backup devices, to WAN optimization appliances, to traditional standalone servers, both in terms of
capital expense (CAPEX) and operational expense (OPEX).
Figure 4 - Today's Complex Web of Data Center Technologies
8. 3. The Legacy Stack Does Not Solve the Data Problem
Approximately 12 disparate products are required in order to deliver Enterprise functionality, protection
and performance. Each of those products is purchased from different vendors, each requires training of
IT professionals; and each is managed from separate management monitor.
Over the last 15 years, there was marked proliferation of appliances and ‘point solutions’ whereby each
only addressed a singular problem. Such appliances all address aspects of the Data Problem. They fall
into 3 sub-categories: data efficiency, data protection, and performance.
1. Data Efficiency appliances: The cost of the WAN was one significant problem, so some companies
offered an appliance to address the optimization of traffic on the WAN. Data protection was
another problem, so another company proposed a different appliance to optimize the local and
remote data backup issue. These two different technologies each addressed merely a subset of the
Data Problem but not all of the Data Problem. When public cloud came into play, another product,
from yet another vendor, was necessary to deduplicate and compress the data for cloud on-ramp
purposes.
2. Data Performance Appliances and sub-systems: Efficient SSD arrays then became a point of
contention. Why the need? Density of the drive had increased dramatically, about 300 fold during
the past decade, yet the RPMs increased only 1.5x thus giving rise to a significant discrepancy
between HDD density and IOPS.
Figure 5 – The I/O Gap
Therefore, IOPS has become one of the most expensive resources in the data center. SSD arrays,
SSD caching, SSD drives in the server and SSD drives in storage arrays have all been added to the
data-center, in order to address the IOPS problem. Most of these SSD arrays and sub-systems are
accompanied by deduplication or compression technologies. Again, each data-efficiency technology
is optimized in order to address a phase in the life-cycle of the data.
3. Data Protection appliances: As requirements for protecting the data increased over the past
decade, a slew of data-protection and restoration emerged. In some data centers, we find
numerous data-protection products from various vendors.
9. Over time, IT organizations have invested these different point technologies to address aspects or
symptoms of the Data Problem. These are bought from and supported by many different vendors, and
managed from as many different management consoles. With these multiple points of management
came the requirement of having dedicated staff with specialized training to maintain the interface of
each stand-alone appliance—and that IT reality required great amounts of CAPEX and OPEX.
Figure 6: The Legacy Stack
Figure 6 illustrates previous attempts at solving the Data Problem having resulted in a very large,
inflexible, complex infrastructure stack.
4. IT Is Turning To the Cloud
By cloud, we mean three core attributes:
1. Automation, orchestration and self-provisioning of IT resources across the organization
2. Elastic infrastructure: grow up, out or in based on consumption
3. A business model supporting #1 and #2
Cloud enables the quick provisioning of IT resources – compute, memory, storage, application services,
data protection services, etc. – from a centralized pool of resources, automated and orchestrated
around the needs of the business.
It is fundamentally a new way of thinking about the delivery of IT services.
10. The reality is that many organizations are turning to the cloud whether IT knows it or not. This is
categorized as “Shadow IT.”
Figure 7: Shadow IT
As IT has been struggling to meet demands and maintain SLAs, the business can no longer wait. With the
growing trend of the Consumerization of IT, employees are used to a certain speed and flexibility. This
expectation leads them to pulling out credit cards for Amazon Web Services or signing up for a free
account on Dropbox, bypassing IT standards and controls.
So what is an IT organization to do? Should it just turn everything over to Amazon or Google?
The big cloud players today do not offer a comprehensive solution to the data problem, which
introduces a dilemma: How can we bring the cloud technology that Amazon and Google are supposedly
implementing into our datacenters when they don’t address some of these problems? There is
disconnect between the big players and the design and implementation of the solution to the Data
Problem.
The ideal datacenter would face the challenge of combining primary storage, servers, backup
deduplication appliances, WAN optimization appliances, SSD acceleration arrays, public cloud gateways,
backup applications, replication applications, and other special purpose appliances and software
applications so that they all run as a unified stack atop a single shared resource pool. If this Data
Problem is truly addressed, atomic IT building blocks can be offered that deliver cloud economics in your
data centers at enterprise scale.
11. 5. SimpliVity OmniCube Solves the Data Problem
SimpliVity’s solution is the revolutionary hyperconverged OmniCube—a scalable, economical, 2U
building block using an x86 server platform that offers all the functionality of traditional IT
infrastructures in one device. The OmniCube is a combined, all-in-one, IT infrastructure platform that
includes storage, compute, networking, hypervisor, real-time deduplication, compression, and optimization
along with powerful data management, data protection, and disaster recovery capabilities.
The OmniCube is an elegant 2U building blocks based on x86 industry-standard systems containing
compute, memory, SSDs, HDDs, and 10GbE interfaces that can be clustered in an efficient scale-out manner
to deliver performance, capacity, availability, and functionality.
The benefits delivered by this framework include performance acceleration by eliminating redundant IOPS,
capacity optimization, and WAN optimization through the deletion of redundant data sent between data
centers and remote offices. The solution delivers cloud economics with Enterprise-class functionality
(performance, reliability, availability, security, data protection, and disaster recovery). SimpliVity refers to
this level integration as Hyperconvergence (3.0)
The solution is designed for high availability with no single point of failure. By combining the powerful
capabilities in a scalable IT building block and leveraging the pool of resources, SimpliVity provides dramatic
improvements in economics and IT simplification when compared to legacy solutions.
Figure 8: SimpliVity’s Simplified Solution
As data is written at inception, the OmniCube deduplicates, compresses, and optimizes it, inline, once
and forever, everywhere. This “Everywhere” is challenging because a global file system and a global
namespace is needed. Most systems deduplicate at one phase of the data life cycle and incur a re-hydration
tax across its lifecycle (primary, backup, archive, WAN, cloud). SimpliVity deduplicates,
compresses and optimizes just once and it persists forever, everywhere.
In order to achieve this quickly—before the data ever hits the disk, which is something no other
company does—we developed the OmniCube Accelerator Card, a PCIe card with FPGA and NVRAM,
12. protected with super capacitors. This architecture allows data processing at near-wire speeds, delivering
enterprise-class performance and reducing latency because of high speed, high availability NVRAM. The
architecture is also extremely efficient because we have our own FGPAs. This means we are not only not
slowing the data, we’re accelerating it—we deduplicate IOPS and data as its written, therefore we write
less data and speed up the process.
There is no longer a need to have separate devices for WAN optimization, backup deduplication, or
cloud gateways. The OmniCube can securely connect to Amazon and also backup and restore to the
Amazon cloud using just our system. OmniCube also requires fewer SSDs in the system than legacy
devices as writes will have already been deduplicated. There are many added protection capabilities,
and additional OmniCubes can be implemented for even higher efficiency and availability. So now—we
have combined, or hyperconverged, all the functionalities that are associated with storage, data, and
data movement.
VMware ESXi currently runs on the OmniCube system; however, KVM and Hyper-V will be added in the
future. Each OmniCube is operated with a SimpliVity controller with VM workloads running on the
platform. OmniCube includes a simple policy-based framework to manage all the backups in the system.
The backup policy for a virtual machine specifies how frequently backups are taken, how long they are
kept, and in which data center they are stored (either local or a remote data center in the Federation).
The public cloud is simply another destination option. All the data that moves is compressed and
optimized, once and forever, everywhere, achieving effortless scalability and mobility.
6. SimpliVity’s Three Core Innovations
Figure 9 below illustrates how OmniCube encompasses three core innovations that fundamentally solve the
Data Problem in today’s datacenters and enterprises.
Figure 9: SimpliVity’s Core Innovations
13. 1. Data Virtualization Platform
The core technology that performs inline data deduplication, compression, and optimization* on all
data at inception across all phases of the data lifecycle (primary, backup, WAN, archive, and on the
cloud), across all tiers within a system (DRAM, Flash/SSD, and HDD), all handled with fine data
granularity of just 4KB-8KB.
a. Reduce IOPS to SSD/flash or HDD
b. Reduce capacity and associated space and power
c. Enablement of global mobility of VMs and data, at a fraction of the time and cost
d. *Optimization: technology that strips the data of overhead that is injected by the Operating
System and the Virtualization stack (for example, the vSwap file), thus contributing to the
efficiency of IOPS, storage and WAN transfer.
2. Hyperconvergence
A single software stack that combines the functionality of up to 12 different products in one,
running efficiently atop a single shared x86 resource pool and leveraging a commodity server
platform to deliver Enterprise IT. The solution delivers Enterprise functionality, protection and
performance on x86 commodity servers. Our customers are benefiting from 3x TCO savings based
on acquisition cost of IT infrastructure, cost of labor, space, and power. Additionally, a low-cost
10GE network is sufficient in order to run a high performance, high functionality IT.
3. Global Federated Management
An intelligent network of collaborative systems that provides massive scale-out capabilities as well
as VM-centric management through a single unified interface for the entire global infrastructure. A
key differentiator with the OmniCube GUI is that the management interface is fully integrated with
VMware vCenter as a plug-in. A single administrator can manage all aspects of the OmniCube from
within vCenter.
Figure 10 - Global Federated Architecture
Figure 10 also shows three OmniCube systems hosting multiple VMs along with a SimpliVity Cloud instance
for efficient, secure Backups in the Public Cloud. Figure 10 demonstrates that OmniCube allows customers
14. to leverage their existing investment of servers for hosting VMs and applications while taking advantage of
the rich functionality of OmniCube. When more resources are needed, more OmniCube nodes can be
seamlessly added to the Federation, thereby dynamically expanding the shared resource pool. Similarly, if
resources need to be consolidated within the Federation, customers can easily move VMs using vMotion
and SimpliVity handles the task of dynamically and efficiently migrating the data across the consolidated
resource pool.
The result of SimpliVity’s three innovations is the market’s most efficient infrastructure for the modern,
agile datacenter—a globally federated hyperconverged IT platform that enables VM-centric global
management of all VMs, their data, and the underlying infrastructure.
Figure 11 – Before and After with SimpliVity
15. 7. Data Virtualization Platform
As stated in Section 6 above, the Data Virtualization Platform is the core technology that performs inline
data deduplication, compression, and optimization on all data at inception across all phases of the data
lifecycle (primary, backup, WAN, archive, and on the cloud), across all tiers within a system (DRAM,
Flash/SSD, and HDD), all handled with fine data granularity of just 4KB-8KB.
Here we’ll go into more technical detail on the need for, and ultimately benefit provided by the SimpliVity
Data Virtualization Platform.
7.1 Technology Overview
The need for a lighter data architecture—one that fosters mobility rather than inhibits it—has been clear for
some time. Many have seen great promise in data deduplication and compression—and have recognized
that if done well, these technologies can facilitate lighter-weight, mobile data structures. Optimization holds
further promise as a means of intelligently managing data based on the anticipated usage of it by the
applications it serves. Following are brief definitions of these technologies:
A. Deduplication—the process of finding and eliminating redundant data within a given data set in
reference to the whole available repository—holds great promise in delivering a light-weight,
mobile data structure and therefore is seen as a key to solving the complexity crisis by addressing
the root cause.
B. Compression—the process of finding and eliminating redundant data within a given data set, in
relation to other data within the same dataset, is a simpler problem, but provides complimentary
value.
C. Optimization—the intelligent treatment of data based on its anticipated use by an application.
Systems that can identify file types and make real-time decisions about whether and where to store
that data can achieve overall improved storage efficiency, performance, and bandwidth usage.
Specifically, deduplication, compression and optimization have several key benefits that address the core
requirements of today’s data center:
x More efficient use of the SSD storage cache. A deduplication process that operates at the right
point in the data stream can reduce the footprint on the cache, improving overall system-wide
performance.
x Dramatic bandwidth reduction on replication between sites. Twenty years ago, the IT
organization was dedicated to a single primary data center, but today, almost all IT teams
manage multiple sites. A fundamental requirement of the infrastructure, then, is fostering
efficient data transfer among sites. Deduplicating data before it is sent to a remote site makes
the transfer itself more efficient and saves significant bandwidth resources.
x Enhanced data mobility. A fundamental principle of server virtualization is the mobility of the
VMs, but coarse-grain data structures significantly block mobility in a traditional infrastructure
environment. When the data is deduplicated, it is easier to move VMs from one server to
another, and it is easier to move data in and out of the cloud for the same reason.
x Efficient storage utilization. Required capacity can be reduced 2-3X in standard primary use
cases based on the effective use of deduplication, compression, and optimization.
16. x Enhanced performance given that less actual data needs to be written to disk or read from disk.
This is amplified in application environments such as Virtual Desktop Infrastructure (VDI), where
“boot storm” can generate multiple GB of random reads from disk. With deduplication,
compression, and optimization, that can be reduced to tens of MB.
x Enhanced “time-to-data”. Achieve faster access to data when performing migrations or when
recovering from a remote site or the cloud.
The above list enumerates the great potential value of deduplication, compression, and optimization across
a number of areas. This may be counter-intuitive given that deduplication technologies have historically
been designed to optimize for HDD capacity.
7.2 Deduplication, Compression, and Optimization Today
When introduced to the market in the mid-2000s, deduplication was designated entirely for backup. In this
use case, optimizing for capacity is crucial, given massive redundancy of data and the ever increasing
volume of data to be backed up and retained.
Deduplication then spread to other isolated phases of the data lifecycle. It has been implemented as
resource-intensive operations that have been implemented in different products, by different vendors, each
addressing a single specific problem: deduplication of backup data, or deduplication of data across the
WAN, or deduplication long-term archives.
Despite the maturity of deduplication, and the great capacity and performance benefits therein, no vendor
has thus far comprehensively solved the deduplication challenge in primary data. Some products apply
deduplication only within the SSD tier, and therefore only offer limited benefits in terms of overall
efficiency. Others apply compression technology and incorrectly use the term “deduplication”. In primary
storage systems, optimizing for disk capacity is a relatively lower priority. Hard Disk IOPS are a much more
expensive system resource than HDD capacity.
As a result of the latency that deduplication may impose, many have deployed it as a “post-process,” which
severely limits other operations such as replication and backup. Most of these sub-optimal
implementations are a result of adding deduplication to an existing legacy architecture, rather than
developing it as the foundation for the overall 21st Century architecture.
The various fragmented work-arounds that vendors have delivered have varying levels of value, but fall
short of solving the underlying problem; they ultimately do not deliver a truly fine-grained and mobile data
infrastructure. IT teams can be left with higher acquisition costs and even more complexity as they manage
partial deduplication amidst their other infrastructure burdens.
All of this points in one direction: 21st century data has to be deduplicated, compressed, and optimized at
the primary storage level, and no later. When data is deduplicated across all tiers right from the point of
inception, it has significant resource-saving ramifications downstream, and opens up the advanced
functionality required for today’s virtualized world.
7.3 SimpliVity Data Virtualization Platform
Rather than taking an existing data architecture and trying to build-in deduplication, compression and
optimization, SimpliVity took the inverse approach. As a first step, it designed the core technology that
17. performs real-time deduplication and compression on primary data, in real-time, without impact to
performance or latency (see below, the OmniCube Accelerator Card), and built an entire globally federated
data architecture around that foundation that manages the resulting fine-grained data elements across a
Global Federation of systems.
In doing so, it addressed all of the core requirements for truly effective deduplication, compression and
optimization for the primary production infrastructure system and beyond:
x Real-time
x Once and forever (no need for a second pass, or hydration/dehydration inefficiencies)
x Across all tiers of data within a system
x Across all datasets
x Across all locations
x Including on the Public Cloud
x Without impacting performance
In delivering the Data Virtualization Platform, SimpliVity is realizing the potential of well-implemented
deduplication, compression, and optimization of primary data. In addition to disk capacity, the Data
Virtualization Platform optimizes HDD IOPS, flash capacity, DRAM capacity, and WAN capacity.
In so doing, SimpliVity’s technology is going far beyond capacity efficiency. What may at first seem counter-intuitive,
the Data Virtualization Platform actually improves system performance. With SimpliVity,
deduplication, compression, and optimization occur before data is written to the HDD, thus preserving the
precious HDD IOPS.
7.3.1 The Starting Point: Real-time Deduplication, Compression and Optimization without Impact
to Performance
The Data Virtualization Platform performs deduplication, compression and optimization in real-time, as the
data is first written into the OmniCube datastore. This contrasts to a more prevalent approach called post-process
deduplication, which allows data to be written first without deduplication and at some later stage,
performs the deduplication process. The big problem with post-processing deduplication is that it
introduces a lag where there was none before. Businesses are presented with the choice to replicate data
before deduplicating it or waiting to replicate until the deduplication process is complete. But neither
option is sufficient: replicating before deduplicating defeats the purpose of deduplicating at all, and waiting
to replicate can create RPO (Recovery Point Objective) issues.
Given the clear superiority (and elegance) of performing deduplication real-time, why is it unusual? In a
word, performance. Deduplication is a resource-intensive process. As data enters the system, it must be
scanned, analyzed, compared to an index or table that has cataloged all existing blocks in the data set, and
then acted upon (either deleted if redundant, or written if new). Pointers and indexes need to be updated
in real-time such that the system can keep track of all data elements in all their locations, while maintaining
an understanding of the full data sets (pre-deduplication) that have been stored in the system.
The challenge is augmented if we wish to maximize data-efficiency by focusing the architecture on granular
4KB or 8KB data sets (which is the original size at which data is written by the application). A system
managing 4KB blocks and ingesting data at 400MB/s needs to perform 100,000 such operations per second.
18. Given the challenge, it is understandable that many vendors have opted to conduct this operation out-of-band,
so as not to impact performance. This is a challenge that SimpliVity addressed head-on and resolved.
7.3.2 OmniCube Accelerator Card
SimpliVity’s real-time deduplication breakthrough is the OmniCube Accelerator Card (OAC), a specially
architected SimpliVity PCIe module that processes all writes and manages the compute intensive tasks of
deduplication and compression. All data that is written to the OmniCube datastore first passes through the
OAC at inception, as it is created.
The practical effect of real-time deduplication is that the Data Virtualization Platform processes data
elements that are between 4KB and 8KB in size, compared to the 10-20MB of traditional architectures, i.e.
2,000 times more efficient. The data is thus “born” to be mobile from the beginning, and remains so
throughout its lifecycle within the OmniCube Global Federation.
Within a given OmniCube system, deduplication makes each storage media tier more efficient— DRAM,
Flash, SSD, and HDD—thereby dramatically lowering the cost of the system compared to traditional
offerings.
While deduplication within a single OmniCube system provides great efficiencies and cost savings, the
additionally groundbreaking value of OmniCube lies in the Global Federation—the network of connected
OmniCube systems that provide High Availability (HA), resource sharing, simplified scale-out, and replication
for VM movement and Disaster Recovery (DR).
Additionally, with deduplication at the core, the Data Virtualization Platform has been designed and
optimized for managing a very large set of fine-grained data elements, across a Federation of systems that
are both local (within the same data center) and remote (dispersed data centers), including the Public
Cloud.
Designing the overall data architecture around the deduplication, compression and optimization engine has
ensured that the value of deduplication pervades all media, all tiers (primary, backup, and archive), and all
locations.
7.3.3 Enhancing the Value through Optimization
While deduplication is the fundamental core, the Data Virtualization Platform further enhances the CAPEX
and OPEX savings enabled with OmniCube by delivering remarkable efficiencies through “operating-system
and virtualization-aware” optimizations. The optimizations within OmniCube deliver similar effects to
deduplication in a different way—they identify data that need not be copied, or replicated, and take data-specific
actions to improve the overall efficiency of the system.
Given that OmniCube today is optimized for the VMware environment, most such optimizations stem from
awareness of VMware specific content or commands. For example, .vswp files, though important to the
functionality of each individual VM, do not need to be backed up or replicated across sites. Thus, when
preparing to backup or replicate a given VM from one site to another, the Data Virtualization Platform
recognizes the .vswp file associated with a VM, and eliminates that data from the transfer - saving time,
bandwidth and capacity. Other optimizations are similar in nature— leveraging the Data Virtualization
Platform’s ability to find and make real-time decisions on common data types within a VMware
19. environment.
8. Global Federated Management
Beyond the global enhancements provided by the Data Virtualization Platform as described in Section 7
above whereby data is deduplicated, compressed, and optimized across all sites and all stages of the data
lifecycle, the SimpliVity global federation also provides extensive operational benefits.
The SimpliVity solution includes a robust, comprehensive management framework. The design is to simplify
IT and make the solution easy to manage within and across data centers and remote offices. The design
focuses on the global federated deployment, and administrators can easily traverse the OmniCube
Federation from within VMware vCenter.
With OmniCube, administrators can easily view and manage applications as well as VMs using simple
operations. All analysis, reporting, actions, and management tasks in the SimpliVity OmniCube are VM-centric
to eliminate the complexity that exists between vSphere and traditional storage arrays and storage
area networks. This means all storage related policies, actions, and monitoring are accomplished on a per-
VM basis across the multi-site federated network. One user can manage the entire global infrastructure
spanning one or multiple sites through one, simple interface. Policy and automation capabilities in the
management layer enable dramatic improvements in operational efficiency, productivity gains, and the
simplification of IT.
Examples of the easy-to-use interface, familiar to a VMware Administrator, are shown below. The
Federation View shows a representation of each data center in the federation along with the connections
between data centers. Note that there are several private vSphere data centers and there is one instance of
an Amazon AWS public cloud that hosts the SimpliVity OmniCube for Amazon. This illustrates how
customers can have a hybrid cloud deployment within the federation whereby low cost backups can be
archived securely and efficiently in cloud infrastructure.
20. Figure 12 – The Federation View
9. Path to Hyper Convergence (v 3.0)
SimpliVity delivers hyperconverged infrastructure for the Software Defined Data Center. We see the
converged infrastructure evolution as having traced the following progression.
Convergence 1.0 endeavors included servers, storage, and switch with VMware, not including data
protection or data efficiency appliances. The benefits from 1.0 are reduced labor costs associated with
managing the product; however, the IOPS are still very costly.
.
Figure 13 – Integrated Systems 1.0
21. Convergence (2.0) provides servers, storage, and switch, but with a virtualized environment of all the
resources. There is now the benefit of a single shared resource pool that enhances efficiencies;
however, the rest of the appliances for protection and efficiency are not part of this scope and virtual
storage appliances are running on a server with a clustered file system. Therefore, the Data Problem is
still not addressed.
Figure 14 – Partial Convergence 2.0
SimpliVity proposes Convergence 3.0, or the whole of the legacy stack in one box, including servers,
storage, switch, deduplication, backup, and a WAN function on x86 resources with global scalability.
Figure 15 – Hyperconvergence 3.0
The final destination in the evolution is one that delivers true hyperconverged infrastructure for the
Software Defined Data Center, and SimpliVity is the first and only vendor executing this vision and
delivering the total solution with OmniCube. SimpliVity refers to this as "Hyperconvergence 3.0."
22. Figure 16 – The Path to Hyperconvergence and SDDC
Interestingly and not at all surprisingly, the leading players of the prior phases of convergence 1.0 and
2.0, VCE and Nutanix, respectively, have each invested far less in their technologies until they became
Generally Available (GA). VCE took about 8 months to launch their Vblock. Nutanix, approximately 18
months (founded in September 2009 and announced first VDI shipment in April 2011). SimpliVity, on the
other hand, invested 42 months in the delivery of its platform on GA basis:
Figure 17 – The History of Convergence
23. 10. Summary
Enterprise data centers require much functionality in order to deliver IT services. In addition to
rudimentary servers, storage, server virtualization and networking, numerous appliances and
applications have been added in order to address: Protection, Data Efficiency (about 3-5 different
deduplication/compression products for different phases of the data life-cycle); Performance and
Global Unified Management. This has caused significant complexity and cost.
Each technology requires support, maintenance, licensing, power, cooling—not to mention a set of
dedicated resources capable of administrating and maintaining the elements.
CIOs want simplicity, without compromising capabilities. What’s required is a combination of x86 based,
Cloud/Web economics, without compromising Enterprise capabilities: Data Protection, Data Efficiency,
Performance and Global Unified Management. SimpliVity is the first and only company to deliver the
Best of Both Worlds: Cloud Economics and Enterprise Capabilities. This is enabled via SimpliVity’s Data
Virtualization Platform.
The net benefits of the SimpliVity OmniCube solution include the following:
x Simplified IT and 3x TCO savings.
x Enterprise performance, reliability, and availability running on x86 commodity resources of
your choice, under the virtualization and management of your choice.
x Global unified management.
x Flexibility in terms of form-factor and deployment options.
Through infrastructure consolidation, increased effectiveness of both physical and human resources, and
decreased complexity, SimpliVity can help organizations take on the challenges of maximizing efficiency
while reducing costs.