Ruckus Wireless Releases "Zap" Wireless Performance Tool to Open Source
New Test Tool Goes Beyond the Average to Accurately Measure and Report Critical Wireless Throughput Variations
SUNNYVALE, CA - January 4, 2010 – Ruckus Wireless™ announced today that is has released its popular “Zap” wireless performance testing program to the Open Source Community to encourage further development of advanced testing tools that provide a better understanding of actual wireless network performance.
Originally developed by Ruckus engineers to characterize wireless behavior of real-time IP-based video streaming applications, Zap is a wireless performance measurement utility designed to determine wireless network signal performance accurately over time, space and frequency.
By design, Zap lets network planners test sustained throughput of an existing wireless network and determine the true, sustained and worst-case performance that it is capable of delivering 99.5 percent of the time. Using Zap, organizers can also predict the real-life performance of a system before deployment.
“With wireless you need to understand the statistical throughput distribution in order to really characterize performance. Zap gives you that. Other performance testing tools only tell you average throughput, which is often irrelevant to demanding applications,” said Bill Kish, chief technology officer and co-founder of Ruckus Wireless. “As good as Zap is, by releasing the code as open source, we believe the software community can make it even better, perhaps even incorporate it into new commercial testing tools. Wi-Fi is becoming a critical network access infrastructure and anything that shines a brighter light onto Wi-Fi performance is a good thing for the industry.”
The historic challenge with wireless testing has been the inability to control environmental changes that cause fluctuations in performance. Even in the absence of external interference, the performance of wireless products vary dramatically from channel to channel due to a variety of factors such as regulatory power limits, local digital noise and RF component variation. Because actual wireless performance is inherently statistical in nature, accurate performance testing must account for this random component.
Zap provides a statistical analysis that anticipates the performance of a wireless network by predicting the percent of time and the locations at which performance will be above or below a certain limit.
How Zap Works
Zap works by sending controlled bursts of packets and measuring both packet loss and inter-arrival times. The primary results reported are number of packets lost, total packets received and detailed throughput statistics. Because Zap provides a measure of both throughput and consistency over time and distance, it has particular importance to streaming video, voice and other latency-sensitive applications. Conversely, knowing only average throughput levels will not help predict the performance of a wireless network.
By measuring the maximum throughput of batches of packets, Zap is able to determine the minimum throughput that can be expected at a given percentile. For example, if Zap reports the 99.5 percentile to be 50Mbps, that means statistically, throughput is at or greater than 50Mbps 99.5 percent of the time. For video applications, the ability to determine throughput within the 99.5 percentile gives IT managers and network designers the assurance of the maximum throughput that a given IP wireless network can deliver reliably to ensure picture-perfect viewing.
Zap is currently integrated into Ruckus ZoneFlex™ Smart wireless LAN products as the underlying engine used by SpeedFlex, a Wi-Fi performance diagnostic tool that lets customers quickly determine the uplink and downlink performance and packet loss of any given wireless connection.
Ruckus released the initial version under the Simplified BSD License. Interested parties can download the source code here: http://code.google.com/p/zapwireless/.