The primary function of load balancing is to distribute a workload across multiple computers or a computer cluster, network links, CPUs or other resources. Load balancing helps to achieve maximized application availability, optimized resource utilization, maximized throughput, minimized response times and of course avoiding application server overload. A load balancing appliance accepts traffic on behalf of a group (cluster) of servers and distributes that traffic according to load balancing algorithms and availability servers and application delivering services.
Ethernity’s ENET platform combines load balancing with switch, router, traffic management per VM, wirespeed NAT/APT, timing and traffic monitoring functionality on a single FPGA. Ethernity’s L2/L3/L4 load balancing solution is fundamental to creating scale-out web services. We designed and implemented layer 2/3/4 hierarchical load balancer that runs on FPGA and meets the performance reliability and operational requirements of multi-tenant cloud computing environments. A key component of ENET platform is the ability to support deterministic performance load balancing and packet modification such as NAT that is used for vCPE implementation, together with a dedicated engine that analyzes availability and health of each CPU/VM, off loading this function from CPU, thereby enabling the load balancer to naturally scale with the size of the data center.