The article, Visibility and control in HP Converged Infrastructure: A history of innovation and standards, describes the joint research between HP Labs and CERN that first demonstrated the scalability of packet sampling for monitoring data networks. The article briefly describes some of the factors that led to the adoption of the sFlow standard and goes on to describe the role of sFlow in HP's Converged Infrastructure/FlexFabric architecture.
This article looks at the evolution of the sFlow standard over the last decade and then looks forward to see how sFlow will continue to meet the challenges of scalable performance monitoring in the next decade.
The sFlow standard was developed to monitor high speed switched networks and sFlow's growth has closely tracked developments in Ethernet switching. The chart above plots milestones in the development of sFlow against the growing Ethernet switching market and the adoption of 1 Gigabit, 10 Gigabit and virtual switch technologies.
Ten years ago, the adoption of high speed Ethernet switching had severely limited the value of probes for monitoring network traffic. The sFlow architecture addressed this challenge by embedding instrumentation within the switches in order to provide network-wide visibility. Initially published by InMon Corp. as RFC 3176, the sFlow.org consortium was founded in 2004 in order to further develop and promote solutions based on sFlow technology.
Since 2004, sFlow has grown into the leading, multi-vendor, standard for monitoring high-speed switched networks. The growth in vendor support of sFlow has been driven by the move to 1G and more recently 10G Ethernet switches.
switches with embedded sFlow monitoring. Switch vendors supporting sFlow now include: AlaxalA, Alcatel-Lucent, Allied Telesis, Arista Networks, Blade Network Technologies, Brocade, Dell, D-Link, Enterasys, Extreme Networks, Force10 Networks, Fortinet, Hewlett-Packard, Hitachi, IBM, Juniper Networks, NEC, Netgear, Voltaire and Vyatta.
Strong vendor involvement in the sFlow standard has ensured that new management challenges are quickly addressed. For example, as wireless networking gained popularity, sFlow was extended to provide visibility into wireless networks and available in products by 2007.
The growth in virtualization has led to the adoption of sFlow monitoring in virtual switches, providing visibility in virtualized and cloud networking. Managing converged, virtualized and cloud infrastructures requires a unified view of performance and sFlow was extended to include storage, server and application performance monitoring.
Where will the next decade take sFlow?
Demand for more energy efficiency is driving current efforts to extend sFlow to include power metering.
Expect to see sFlow in an increasing number of 40G and 100G switching products. The sFlow protocol is designed to monitor high speed switch fabrics and provides low cost, wire-speed monitoring at speeds of 100Gbits/s and beyond with the scalability to monitor the large, flat, layer 2 fabrics emerging to support virtualization.
Finally, the unique scalability of sFlow dramatically simplifies management by providing a single, centralized view of performance across all resources in the data center. Measurement eliminates uncertainty and reduces the complexity of managing large systems. An effective monitoring system is the foundation for automation: reducing costs, improving efficiency and optimizing performance in the data center. In future, expect to see sFlow monitoring tightly integrated in data center orchestration tools, fully exploiting the flexibility of virtualization and convergence to automatically adjust to changing workloads. For additional information, the Data center convergence, visibility and control presentation describes the critical role that measurement plays in managing costs and optimizing performance.