Architecting Low Latency Cloud Networks

Authored on: Jan 13, 2012

Download As data centers transition to next generation virtualized & elastic cloud architectures, high performance and resilient cloud networking has become a requirement for delivering always-on, always-available applications.

Over the last decade response time requirements have been rigorously tightened, toward fractions of a second, and both network and compute latencies need to be reduced in parallel. An architectural approach is needed so that response times are consistently and measurably enhanced across a wide set of cloud applications. And because latency optimization is implemented at the infrastructure level, it needs to be future proof to meet latency demands 3 to 5 years out. Furthermore, it is critical that low latency infrastructure fabric be built using standards-based and widely used technologies for broad- based cloud deployments.

The drive for scalable and efficient cloud networks has led to 10Gb Ethernet as the interface of choice for simultaneously transporting data, storage and compute information over a common Ethernet cloud. Arista Networks and Citrix have adopted an architectural approach to building low latency cloud networks. Arista's wire-rate, non-blocking and ultra low latency 1Gb/10GbE switches combine with Citrix's VPX application delivery to enable resilient and multi-application cloud networks.