Why Hyperconverged Infrastructure?
Hyperconverged infrastructure is part of the modernization movement in today’s data centers. Business demands and IT challenges are forcing CXOs to take a longer look at investments that will fuel growth, innovation, agility and competitive advantage. The desire is to transition to an Amazon- or Google-like data center. However, legacy IT infrastructure in siloed organizations cannot deliver cloud-scale IT in the enterprise. A new approach is needed.You’ve virtualized much of your production workloads. You’re on a path to cloud service delivery. But emulating the scale-out architectures of an Amazon, Facebook or Google will require disruption of the traditional vendor landscape. That’s where converged infrastructure comes in. Consolidating IT components into a single optimized platform with centralized management enables increased utilization and lower costs.Leading companies around the world recognize that SimpliVity’s hyperconverged infrastructure and data architecture improves efficiency and agility while dramatically reducing the total cost of ownership. SimpliVity delivers a unique data architecture on hyperconverged x86 building blocks. It’s hyper-simple, hyper-scalable, hyperconverged infrastructure for the modern software-defined data center.
Converged Infrastructure In The Data Center
In the post-virtualization data center, we have misalignment between legacy IT stacks and the needs of virtual workloads. Since siloed physical storage and network assets lack the optimization to support your virtual servers, you overprovision resources. As you virtualize more and more workloads, and the data associated with your workloads grows, your environment cannot keep pace. Throwing more hardware at the problem only adds more complexity and cost, and doesn’t address the real problem.
Converged Infrastructure: The Performance Problem
The one-to-one relationship between a physical server and storage shifts to a many-to-one relationship between virtual machines and a single storage controller. Multiplexing the different IO streams of multiple workloads by the hypervisor creates random IO streams that must compete for resources. This increases IOPS required to service the virtual workloads. To address performance issues, you may add more disk spindles. However, this also increases capacity. This overprovisioning leads to a higher cost per gigabyte of storage allocated to every virtual machine.
Converged Infrastructure: The Capacity Problem
Virtualizing workloads results in an increase in storage capacity requirements. Since virtual machines encapsulate the operating system, application, and data, you aggregate a massive volume of redundant data. This creates a tremendous amount of inefficiency in storage capacity. So too does virtual machine sprawl. The rapid deployment of virtual machines—each requiring an allocation of storage—increases the volume of storage required. As the number of virtual machines increases, so does the associated volume of snapshots consuming storage capacity.
Converged Infrastructure: The Mobility Problem
Your virtual machines are portable. However, virtual machines are tied to the datastore in the virtualization domain, which is tied to siloed physical storage. This can limit the mobility of the virtual machine. To complicate matters further, instead of managing from a virtual machine point of view, you’re managing the virtualized workload’s storage from the point of view of the storage system: LUNs (or NFS mounts), volumes, RAID groups (or aggregates) and physical disks. Therefore, when you configure policies at the LUN level, datastores sharing a LUN inherit the LUN-based policies. When a LUN hosts tens to hundreds of virtual machines, snapshotting or replicating the LUN to capture a single virtual machine copy creates storage capacity and network bandwidth inefficiency.
Converged Infrastructure Creates Efficiency
You want to gain a competitive edge. That’s what cloud service providers like Amazon set out to do when they built out Amazon Web Services. Their edge? They had to crack the code on utility computing to deliver greater efficiency. To achieve it, Amazon Web Services leveraged virtualization and distributed computing using commodity components. This new approach to infrastructure and computing allowed them to develop economies of scale and set lower prices. If you’re running applications on virtualized infrastructure, you’ve likely considered using third-party cloud services versus refreshing your own hardware to improve efficiency and reduce costs. So, which is the right approach? Should you leverage public cloud computing? Or should you build a private cloud-computing environment that delivers the capabilities of large cloud service providers within your own IT environment?Converged Infrastructure helps with the latter. It combines data center components into an appliance form factor, and adds centralized management and the ability to easily scale – it eliminates compatibility issues typical in a legacy, siloed environment. Furthermore, it streamlines purchasing, deployment and use with converged infrastructure. Emulating the architecture, processes and practices of the top cloud service providers starts with converged infrastructure. You can reduce complexity, cycle time and costs. That allows you to change the economics of in-house IT service delivery.
Converged Infrastructure Evolution
What’s the right approach for you? Vendors and their convergence approaches vary.
Legacy Infrastructure Silos Fall Short
Now that you’re virtualized your hardware, your data center requires seamless interaction between infrastructure components and operational staff. Being handicapped with legacy server, storage and networking silos leads to manual intervention, reduced productivity, and duplication of effort. This adds to your operational costs. Convergence eliminates silos of people, process and technology. Converged infrastructure allows you to design, build, and maintain segments of the virtualization stack, while supporting an on-demand growth model.
Partial Converged Infrastructure
Early entrants in the converged infrastructure market are vendors with independent legacy server, storage and networking components. They deliver converged infrastructure consisting of pre-racked and cabled solutions based on a reference architecture. While the design and integration of stack components are simplified, this approach falls short from a management and scale standpoint. They are still separate products—sometimes from separate vendors—to manage and support. Policies are set independently at the hardware level and components scale independently. These converged infrastructure systems have good integration from an interoperability and management standpoint, but the configuration is still rigid with respect to scale, and service and support, which results in higher costs. It’s partially converged infrastructure.
Converged Infrastructure Systems
The next wave of converged infrastructure aggregates compute, storage and SAN functionality into modular appliances based on commodity x86 hardware that scales out by adding appliance “nodes.” Centralized management and policy configuration at the virtual machine level contribute to lower operational costs. This single-vendor converged infrastructure solution also streamlines deployment, and lowers acquisition costs – this system, however, doesn’t fully address the performance and capacity issues. It still uses inefficient methods of writing and reading data to and from storage. Nor does it consider the challenges of capturing, storing, transferring and recovering data copies for backup and disaster recovery.
The Next Generation of Converged Infrastructure: Hyperconvergence
The “third wave” of converged infrastructure delivers the most value. True hyperconvergence is characterized by:
- A single vendor design, delivery and support.It streamlines the acquisition, deployment, management and support of the solution. It also reduces complexity, interoperability issues and operational expenses. SimpliVity architected its hyperconverged infrastructure from the ground up with these efficiencies in mind.
- A single shared resource pool of x86 resources.Combining all IT infrastructure and services below the hypervisor into a single shared pool of x86 resources eliminates the need for discrete IT components. It creates an environment that’s optimized for virtualized applications. And, it creates an environment that reduces costs to enable cloud-level economics.
- Ease of scale.A scalable “building block” approach that expands by adding additional units to meet business demands.
- Centralized Management.The ability to centrally manage virtual environments globally through a single interface is key to improving operational efficiency and reducing operational expenses.
- Hyper-efficient use of resources.Efficient use of resources is accomplished in three ways: 1) eliminate duplicate devices and services, making more efficient use of resources and reducing capital costs; 2) saving IOPS and lowering capacity requirements by deduplicating, compressing and optimizing data inline in real-time; and 3) offloading intensive processing from x86 processors to ensures that maximum CPU resources are available for application requirements.
- VM-centricity.Management shifts to the application or virtual machine, which enables greater mobility, and offers VM-centric policies and management.
- Native data protection.VM-level backup and replication of backup data between sites eliminate the need for third-party backup and replication software and hardware, and backup specialists.
- Software-centric design.Hyperconvergence meets software-defined data center requirements, enabling automation to improve operational efficiency.
Hyperconverged infrastructure addresses the performance, capacity, mobility, and management issues prevalent in previous waves of converged infrastructure. It achieves VM-centricity by tracking what data belongs to which virtual machine, enabling VM-mobility. By eliminating redundant read and write operations, hyperconverged infrastructure achieves performance efficiency. It achieves capacity efficiency by reducing the “footprint” of data on production and backup storage via deduplication, compression and optimization of data at inception. Hyperconverged infrastructure dramatically reduces total cost of ownership. It eliminates siloed technology, enables rapid application deployment, reduces labor-intensive activities, prevents over-purchasing and over-provisioning, and maximizes the infrastructure investment. The data efficiency introduced with deduplication, compression and optimization also improves performance.
Converged Infrastructure in Your Environment
Where can your organization benefit from converged infrastructure? It’s an ideal platform for:
- Data center consolidation, whether you are converging resources within or across data centers, or refreshing your technology infrastructure with an upgrade or expansion.
- Deploying new tier-1 applications or virtualizing applications.
- Implementing Virtual Desktop Infrastructure (VDI).
- Managing remote or branch office (ROBO) infrastructure, or managing your remote disaster recovery site.
- Performing a data migration within or across sites.
- Test and development infrastructure.
SimpliVity Hyperconverged Infrastructure
SimpliVity is a leader in hyperconverged infrastructure for the software-defined data center. Its unique data architecture contributes to a 3x reduction in total cost of ownership. SimpliVity’s Data Virtualization Platform introduces performance and capacity efficiency by eliminating unnecessary IO and redundancy. It deduplicates, compresses and optimizes data at inception, and keeps it in that state for its lifecycle. Native data protection eliminates the need for complex and costly add-on backup software and hardware. You can back up locally or store backups at a remote site—including the public cloud. SimpliVity offers global unified management across multi-node and multi-site hyperconverged infrastructure federations, via a vCenter interface. SimpliVity takes a VM-centric point of view and tracks what data belongs to which virtual machine. This enables greater virtual machine mobility. Apply SimpliVity hyperconvergence to your environment.