Insights

Terms & Definitions

Asynchronous Replication
Asynchronous replication is a process used in server and network storage. Once data has been written to the primary storage site, new writes to that site can be accepted, without having to wait for the secondary or remote storage site to finish its writes. The downside to asynchronous replication is the possibility of data loss if the primary site were to fail before the data has been written to the secondary site. Vcinity’s technology improves Asynchronous Replication tremendously, by replicating the data faster and more reliably than any other technology. This allows our customers to asynchronously replicate more data over greater distances with absolute reliability.

Buffer
Buffer is a memory space reserved for storing packets internal to Vcinity’s Ultimate X™ solutions, providing a traffic-shaping function.

Traffic Shaping
Traffic shaping (also known as packet shaping) is a computer network traffic management technique that delays some or all datagrams to bring them into compliance with a desired traffic profile. Traffic shaping is used to optimize or guarantee performance, improve latency, and/or increase usable bandwidth for some kinds of packets by delaying other kinds. Vcinity’s Ultimate X supports such traffic shaping, hence the necessary packet buffering.

Data at Rest
In simple terms, data at rest is the data that is not currently being modified. Within information technology, it refers to inactive data that is stored physically in any digital form (e.g., in databases, data warehouses, spreadsheets, archives, tapes, off-site backups, mobile devices, etc.) Data at rest is used as a complement to the terms “data in use” and “data in flight/transit” which together define the three states of digital data.

Data in Flight
Data in flight/transit or data in motion is defined into two categories — data that flows over the public or un-trusted network, such as the internet, and data that flows within the confines of a private network, such as a corporate or enterprise Local Area Network (LAN).

Deterministic/Predictable Performance
In data transportation/exchange, Determinism is defined as “the ability to send a piece of information to a destination and receive a response in a repeatable time frame.” Routers forward L3 IP packets by making decisions on a per-hop basis, resulting in non-deterministic, lossy behavior. Probabilistic, hierarchical IP-routed networks are better suited for non-critical bulk applications but not for time-critical ones. Routers support today’s TCP/IP networks, and their performance degrades severely over long distances, partly due to the non-deterministic and lossy network layer. Vcinity’s solutions provide deterministic, lossless, native L2 extension globally to support time-critical applications. These include, but are not limited to media production, financial trading, business continuity, etc.

E-Line/E-LAN
Carrier Ethernet is a marketing term for extensions to Ethernet that enable telecommunications network providers to provide Ethernet services to customers and to utilize Ethernet technology in their networks. Carrier Ethernet standards define E-Line as a service connecting two customer Ethernet ports over a WAN. E-LAN is a multi-point service connecting a set of customer endpoints, giving the appearance to the customer of a bridged Ethernet network connecting the sites.

Global Fabric Extension
Data center fabrics consist of interconnected nodes that look like a “weave” or a “fabric” when viewed collectively on a network diagram. Generally, they exist within the four walls of the data center. Vcinity’s Global Fabric Extension technology extends these local fabric/infrastructure, services and applications across MAN/WAN. Vcinity supports concurrent fabric types and is compatible with any and all WAN services providing ultra-high network utilization and ultra-low latency and jitter.

HPC
High-Performance Computing (HPC) is the term often used for large-scale computers and the simulations and models that run on them. Vcinity uses and abstracts the following HPC technologies to achieve a lossless fabric with deterministic performance:
Parallel File Systems. Distributed file systems, which also are parallel and fault tolerant, stripe and replicate data over multiple servers for high performance and to maintain data integrity. Even if a server fails, no data is lost. The file systems are used in both HPC and high-availability clusters.
RDMA (Remote Direct Memory Access). RDMA is a communications technique that allows data to be transmitted from the memory of one computer to the memory of another computer without passing through either device’s CPU, needing extensive buffering, or calling to an operating system kernel. RDMA has been deployed in HPC applications since early 2000. Today, RDMA is being adopted into commercial applications.

Layer 2 Connection
Layer 2 connection uses L2 addressing (MAC SA/DA, VLAN ID, etc.) to deliver packets to the destination address, unlike L3 connection, which uses L3 (e.g., IP) addressing. Vcinity’s products operate over any layer 1 and layer 2 guaranteed- bandwidth connections.​

MPLS
Multi-protocol Label Switching (MPLS) is a type of data-carrying technique for high-performance telecommunications networks. It directs data from one network node to the next based on short path labels rather than long network addresses, avoiding complex lookups in a routing table. Vcinity’s products and solutions do not compete with MPLS solutions, but work with MPLS using PWE-3 and achieving the same level of performance enhancement compared to standard TCP/IP. TCP/IP uses MPLS as a server layer instead of IP routing so Vcinity solutions still address the TCP/IP performance issues.

Node
Entire Ultimate X, whether it has one or more compute engines, is referred to as a single Ultimate X node. All the Ultimate X components installed at one site are typically considered part of a single node.

Optical Transport Solutions
Vcinity does not compete with Dense Wavelength Division Multiplexing (DWDM), Reconfigurable Optical Add Drop Multiplexer (ROADM) or Packet Optical Transport System (POTS) platforms, but works with them. Optical transport solutions provide the physical reach to truly showcase Vcinity’s “global” fabric reach.

RoCE
RDMA over Converged Ethernet (RoCE) is a network protocol that allows remote direct memory access (RDMA) over an Ethernet network. There are two RoCE versions — RoCE v1 and RoCE v2. RoCE v1 is an Ethernet link layer protocol and hence allows communication between any two hosts in the same Ethernet broadcast domain. RoCE v2 is an internet layer protocol, which means that RoCE v2 packets can be routed. Although the RoCE protocol benefits from the characteristics of a converged Ethernet network, the protocol can also be used on a traditional or non-converged Ethernet network.

Site
Site is the entire physical location at which Ultimate X or other Vcinity solutions are installed.

Synchronous Replication
Synchronous replication is a process used in server and network storage. Data is written to both the primary and secondary storage devices simultaneously. The write is not completed until both targets have acknowledged the write completion. The benefit of synchronous replication is the reduced chance of data loss or integrity problems in the event of a failure. However, this comes at a cost of the application having to wait for the secondary or remote storage site to also finish its writes. Therefore, synchronous replication to remote sites suffers from rather short distance limitations in order for the application to perform acceptably. Vcinity’s technology improves synchronous replication by providing lossless and deterministic data movement, allowing our customers to synchronously replicate more data over greater distances without sacrificing application performance.

Tiered Storage
Tiered storage is the assignment of different categories of data to various types of storage media to maintain optimal performance while reducing the total storage cost. Tiers are determined by a variety of factors, such as performance and cost of the media, physical location, and frequency of data access. Data is assigned or migrated to the appropriate tier of storage based on customer requirements, such as performance, access patterns, or availability policies. In the context of Ultimate X, the embedded drives on Ultimate X act as a faster tier or cache before the data is made accessible or moved across Ultimate X nodes at different locations.