LOAD BALANCING EMBEDDED IN NOVIFLOW SWITCHES
NoviFlow switches implement the next generation networking technology – a programmable forwarding plane with match-action rules in a fully programmable pipeline. This new packet processing platform enables a broad range of new applications beyond the standard L2/L3 routing.
One example of the new capabilities is the ability to implement line-rate load balancing on the network device. NoviFlow switches provide Load Balancing services in the multi Gigi-bit to multi Tera-bit range. This is a level of affordable load balancing that just does not exist in competitive products.
THE OLD SOLUTIONS JUST DON'T WORK ANYMORE
Despite the last twenty years’ breakthroughs in data center compute and storage, or even perhaps because of them, rising network costs remain an inescapable issue. Networking technology lags significantly behind compute and storage in taking advantage of virtualization and disaggregation, resulting rigid all-in-one designs, vendor lock-in, the multiplication of protocols, proprietary interfaces, non-deterministic network behaviour, and a very limited ability to interact meaningfully with the applications and services that use network resources.
One major barrier to reaping the benefits of virtualization has been the lack of an effective, economical approach to balancing traffic loads across Virtualized Network Functions. Current load balancing appliances are not only very expensive, but they are hard to scale, costly to manage, slow to reconfigure, and add significant latency at network ingress/egress points. Unlike compute and storage, the network's ability to balance traffic loads neither scales-up, nor scales out, placing limitations on the benefits of Hyperscale architectures and causing major headaches to data center and network managers
IT'S TIME TO ALLOCATE LOAD BALANCING TO THE INTELLIGENT SWITCH
NoviFlow’s NoviSwitches implement load balancing as part of the standard flow handling of all incoming and outgoing traffic at line rate! We have implemented symmetrical hashing functions in-switch to optimize load balancing consistently across the entire network fabric. Note that all three offer the best price-performance profiles for the specific task at hand. Over a typical large scale router this results in savings of up to 75% on hardware costs and 65% in operational costs!
Why not run the forwarding plane on x86? The NPU-based programmable pipeline in NoviFlow switches is optimized for packet processing, executing many of the more complex tasks expected of switches and routers faster by a factor of as many as two or three orders of magnitude, and at significantly reduced costs. Also, since the hashing and load balancing function are directly programmable from standard OpenFlow controllers or via CLI, when combined with the powerful flow handling, user definable matching and packet handling, metering and tunneling capabilities (amongst many other features) NoviFlow’s NoviSwitch solution can be used to manage almost any load balancing tasks, even for services that have yet to be devised!
LOAD BALANCING IN PIPELINE
NoviFlow switches, based on the OpenFlow SDN standards, enable multi-table programmable pipelines. This capability is used to craft a Load Balancing solution as part of the pipeline. One of the tables is programmed to map packet flows to target services.
This mapping is part of the line-rate packet processing. Thus, Load Balancing becomes an embedded function with the NoviFlow network device.