Standard traffic shaping is unable to effectively smooth out most bursts, as many occur on a millisecond time-scale (micro-bursts), and the granularity of most shapers is not sufficient to process traffic at this speed. However, an emerging alternative called micro-shaping - optimizing bandwidth on a per-packet basis - is now able to cost-effectively groom micro-bursts in a lossless manner.
Micro-shaping is a single-ended technique that combines hierarchical QoS (H-QoS) mapping with 1 ppm+ packet processing, normally performed in a small appliance with a programmable Field Programmable Gate Array (FPGA) processor instead of merchant silicon.
On a Gigabit Ethernet link, 1 ppm means the processor is running 5x faster than the rate at which packets are received. This processing speed is 1,000x faster than millisecond-length micro-bursts, allowing lower-priority packets to be precisely interleaved into flows where instantaneous capacity is not fully used by higher-priority streams. The result is best-possible bandwidth capacity utilization (fill) without the packet discard associated with more 'lumpy', coarse shaping techniques. H-QoS flow prioritization ensures no latency is added to priority traffic.
Standardized by the MEF 10.3 specification, H-QoS is highly efficient approach to per-flow prioritization and queuing: a bandwidth 'envelop' is intelligently shared between all flow priorities. CIR is consumed hierarchically - any higher-priority flows' unused CIR is passed to the next lower priority flow, and so on, until all flows have maximized the use of the total service CIR. Any remaining CIR in the envelop is added to the available EIR, and the same process is repeated.
Reap the Bandwidth
Micro-shaping's combination of H-QoS priority queuing and ultra-fast packet processing is potent.
In a simple test, Speedtest.net was used to measure uplink bandwidth performance over 15M and 30Mbps ISP connections. Micro-shaped up-link traffic reaches full link capacity, while unconditioned traffic uses only a fraction of the available bandwidth. Normally, the customer is getting only 25% of what they are paying for. Micro-shaping increased typical throughput by nearly 600%.
In controlled tests with precise and accurate instruments, micro-shaping's effect on bandwidth performance optimization is even more dramatic. An improvement of up to 800% can be gained when applied to TCP traffic flows - accounting for over 98% of Internet traffic since 2002 (Source: DongJin Lee, Brian E. Carpenter, Nevil Brownlee, 2011).
Too Easy? Finally, Something Simple!
The best solutions to many problems are the simplest. Compared to WAN-optimization techniques that require expensive appliances or subject to performance variation if virtualized, affordable micro-shaping-capable hardware can optimize bandwidth performance without variation or setup complexity.
Properly implemented, micro shaping-based Bandwidth Performance Optimization can significantly improve throughput in a wide variety of applications over regional, national and international networks, This technique has the highest impact where bandwidth is expensive, cannot be easily increased, or where uplink performance is critical to application responsiveness or overall QoS.
Sign up for Computerworld eNewsletters.