Five trends in network are driving the transition to software defined networking and programmability.
• User, device and application mobility; • Cloud computing and service; • Consumerization of IT; • Changing traffic patterns within data centers; • And agile service delivery.
The trends stretch across multiple markets, including enterprise, service provider, cloud provider, massively scalable data centers -- like those found at Google, Facebook, Amazon, etc. -- and academia/research. And they require dynamic network adaptability and flexibility and scale, with reduced cost, complexity and increasing vendor independence, proponents say.
IT'S BIG: OpenFlow and SDN: Networking's Future?
According to Cisco, which just released its ONE programmability architecture, enterprises need network programmability to automate the operation of private cloud deployments. These deployments include virtual workloads, virtual desktop infrastructures, and the orchestration of security profiles across them.
And within the enterprise data center, traffic patterns have changed from the "north-south" directions of client/server to "east-west," in which applications access different databases and servers before delivering data back to the client. The Open Networking Foundation says this, as well as the increasing use of personal devices to access corporate data -- the BYOD phenomenon -- and the deployment of private, public and hybrid cloud infrastructures and services is also changing traffic patterns, requiring the automation, rapid reconfigurability and simplified extendability SDNs provide.
Other SDN/programmability/network virtualization players say SDNs and the applications they enable can relieve VLAN exhaustion, facilitate data center interconnect and disaster recovery, allow for granular, policy-based security, network isolation, service interposition, deterministic application performance and customization, among others. Policy-based security is particularly important to the BYOD trend; as the ONF notes, enterprise IT is under pressure to accommodate personal devices in a fine-grained manner while protecting corporate data and intellectual property, and meeting compliance mandates.
Service providers need SDNs for agile service delivery, proponents say. SDNs and network programmability can enable policy-based control and analytical data capture to help optimize and monetize service delivery, they say. Cloud service providers and webscale companies like Google, Facebook and Yahoo to ease or automate network configuration and reconfiguration, and quickly add more functionality without manually touching each and every switch or router in the network.
Such companies can use OpenFlow and SDNs to reroute traffic, balance traffic loads, provide bandwidth on demand for peak requirements, execute policies to scale and segregate the networks of different data center or cloud tenants, and connect subscribers to content and services. Cloud providers in particular require programmability to support scalable multi-tenant environments through automated provisioning and virtualization overlays that abstract complicated and distributed physical infrastructures from function.
From an IT perspective, deployment of and access to cloud services can be facilitated by SDNs that enable "elastic scaling" of compute, storage and network resources using a common suite of tools from a common viewpoint, according to the ONF. This is particularly important as organizations stress increased security, compliance, and auditing in cloud environments, or when abrupt changes emerge as businesses reorganize, consolidate or merge.
Massively scalable data centers are said by Cisco to require network flow management enabled through customization using programmatic APIs to provide deep insight into network traffic. And academia and research require network "slicing," or partitioning to separate experimental network use -- i.e., to investigate applicability of OpenFlow or SDNs -- from production networks.
In both scenarios, big data plays a key role in requiring SDNs or network programmability. SDNs can help steer traffic between thousands of servers processing massive datasets in parallel; and can help data center networks scale more efficiently while maintaining server-to-server, server-to-storage, and server/storage-to-network connectivity.
Whatever the requirement, today's networks are not up to the task of providing the adaptability and scale that SDNs promise, according to the ONF:
"The explosion of mobile devices and content, server virtualization, and advent of cloud services are among the trends driving the networking industry to reexamine traditional network architectures. Many conventional networks are hierarchical, built with tiers of Ethernet switches arranged in a tree structure. This design made sense when client-server computing was dominant, but such a static architecture is ill-suited to the dynamic computing and storage needs of today's enterprise data centers, campuses, and carrier environments."
Read more about data center in Network World's Data Center section.