Assessment of Data Path Implementations for Download and Streaming

Distributed multimedia streaming systems are increasingly popular due to technological advances, and numerous streaming services are available today. On servers or proxy caches, there is a huge scaling challenge in supporting thousands of concurrent users that request delivery of high-rate, time-dependent data like audio and video, because this requires transfers of large amounts of data through several sub-systems within a streaming node. Since the speed increase for memory accesses does not follow suite with the CPU speed, copy operations can be a severe limiting factor on the streaming performance of off-the-shelf operating systems, which still have only limited support for data paths that have been optimized for streaming despite previous research proposals. We observe furthermore that while CPU speed continues to increase, system call overhead has grown as well, adding to the cost of data movement. In this paper, we therefore revisit the data movement problem and provide a comprehensive evaluation of possible streaming data I/O paths in Linux 2.6 kernel. We have implemented and evaluated enhanced mechanisms and show how to provide support for more efficient memory usage and reduction of user/kernel space switches for streaming applications.