37 software-defined storage terms you need to know, Part 1
If you’ve ever wondered what software-defined storage is, or have ever been lost deciphering storage terminology, you’re in the right place. There are some really great resources online – such as Techopedia, and the Tech Target glossaries – however to help cut directly to some of the most important concepts in SDS, we’ve created a two-part glossary containing 37 of the key terms you should know to understand how the technology works.
Read on for part one, and keep your eyes on Hedvig’s blog for part two in the next couple weeks. We’ll also include a downloadable PDF containing all 37 terms when we post the second installment.
Without further ado, here is part one of Hedvig’s software-defined storage glossary.
STORAGE TYPES AND FORM FACTORS
Companies typically use several types of storage to meet the various capacity, performance and availability needs of their applications. Software-defined storage (SDS) aims to consolidate all these flavors and forms into one solution that is centrally managed, reducing the time and costs required to provision and administer storage.
Block storage – A type of storage that writes data and files to disk in small chunks called blocks – each block with its own address. Block storage is typically abstracted and managed by a file system or application on a host that interacts with the disk media using SCSI (Small Computer System Interface) commands. Unlike an object (see object-based storage), a block of data does not contain metadata to provide context for what that block of data is. Examples of block storage include storage area networks (SANs), iSCSI (Internet Small Computer System Interface) and local disks.
Commodity / whitebox hardware – Off-the-shelf server hardware that is inexpensive, easy to maintain and replace, and generally compatible with other devices. A major benefit of SDS is that organizations reduce costs by delivering storage services via software stacks on clusters of commodity hardware. Over time, instead of doing forklift replacements of storage hardware, with software-defined storage you can instead renew and modernize by incorporating the latest, state-of-the-art commodity servers and removing older nodes with zero downtime. Examples of commodity hardware include x86 and ARM servers.
File storage – A type of storage presented, controlled, and managed via a file system – typically NFS (Network File System), or SMB (Server Message Block) commonly referred to as CIFS (Common Internet File System). File storage manages the layout and structure of the files and directories on the physical storage. It also facilitates file sharing so many users and systems can access the storage resource at the same time. File-based storage is typically used with network-attached storage (NAS) systems.
Flash / solid state drive (SSD) – A storage device that stores persistent data on nonvolatile solid-state flash memory. Unlike spinning electromechanical disks (i.e., hard disk drives), SSDs have no moving parts. SSDs also typically run quietly, store and access data more quickly, have less latency and are more reliable and durable than electromechanical disks. Since the technology is more advanced, the cost of SSDs is usually higher.
Object storage – A type of storage where data is managed as “objects” containing three parts: the data itself (i.e., an image or brochure), its metadata, and an identifier or address that allows the object to be found in a distributed system. Object-based storage is well-suited for managing large amounts of unstructured data, including email messages, word processing documents, social media and audio files. Object storage is also frequently used for data archiving systems that need to store large amounts of infrequently accessed data for an extended period of time.
Software-defined storage (SDS) – Storage technology that is installed and managed as software on commodity hardware rather than purchased and deployed as a distinct hardware storage array. By abstracting the storage hardware from the software, SDS enables organizations to allocate storage infrastructure resources dynamically and efficiently to match application needs.
Storage node – An individual compute server that is a participant in a storage cluster – sometimes referred to as cluster node.
Virtual disk – A virtual disk or vdisk is an abstracted logical disk volume presented to a computer or application for read/write use. Some SDS solutions enable advanced policies and features such as deduplication to be set on a per-virtual disk basis.
There are many ways companies deploy infrastructure in their data centers. A main objective of SDS is to let companies easily use whatever architecture meets their needs at a given time.
Brownfield – A term that describes deployment of new software or systems that leverage established or existing assets. An example of a brownfield deployment is software-defined storage that utilizes a traditional storage array as a part of the system.
Distributed system – A cluster of autonomous computers networked together to create a single unified system. In a distributed system, networked computers coordinate activities and share resources to support a common workload. The goals of distributed systems are to maximize performance and scalability, ensure fault tolerance, and enable resource availability. Examples of distributed systems include Amazon Dynamo, Google MapReduce, Apache Hadoop, and the Hedvig Distributed Storage Platform.
Greenfield – A term that describes the deployment of a new storage system or assets in an environment where no previous ones exist.
Hybrid cloud – A cloud computing environment in which private cloud resources (e.g., on-premise data center) are managed and utilized together with resources provisioned in a public cloud (e.g., Amazon Web Services).
Hyperconverged – A system architecture that combines software-defined compute and software-defined storage together on a commodity server to form a simplified, scale-out, data center building block. The “hyper” in hyperconvergence comes from hypervisor – the server virtualization component of the solution.
Hyperscale – An architecture where software-defined compute and software-defined storage scale independently of each other. A hyperscale architecture is well-suited for achieving elasticity because it decouples storage capacity from compute capacity. Hyperscale architectures underpin web giants including Google and Amazon and is being increasingly adopted by other enterprises as a means to efficiently scale or contract an environment over time.
Storage cluster – A group of storage nodes that form a single scale-out storage resource pool. A storage cluster leverages the aggregate capacity and horsepower of many networked commodity, whitebox servers.
Software-defined data center (SDDC) – A data center where all infrastructure elements – storage, compute, networking, etc. – are virtualized and delivered as a service. With IT-as-a-service (ITaaS), all components can be provisioned, operated, and managed (in short, defined) on the fly as needed, typically through an application programming interface (API). The application layer is freed from the constraints of physical infrastructure, and the physical hosts or data center may change at any given time without interruption to services. By contrast, in traditional data centers, infrastructure is usually fixed, and defined by hardware and devices. Software-defined data centers are implicitly hybrid, elastic and include self-provisioning by default. The software-defined data center is increasingly considered to be the next era of IT infrastructure.
In the meantime, download this Forrester whitepaper to learn more about software-defined storage trends, adoption, and use cases.