PRISM Proxies for Internet Streaming Media J Kurose

PRISM: Proxies for Internet Streaming Media J. Kurose, P. Shenoy, D. Towsley (UMass/Amherst) L. Gao (Smith College) G. Hjalmtysson, J. Rexford (AT&T Research - Labs)

Outline goals of project o services for streaming media o research issues o progress to date o

Vision: enabling/enhancing a new service infrastructure 2 nd generation service: proxy between server, clients client-tailored services enhanced scalability First generation servers o o o single server, multiple clients end-end principle homogeneity in offered service

Proxy Services: Motivation Improved performance o protect user from poor throughput, delay, loss o exploit short RTT to client o exploit single provider of proxy-client path Value-added services o services not available at server, tailored to client , transcoding, error recovery, interactive services Exploit inside information o knowledge of Qo. S/provisioning on proxy-client path o knowledge of client bandwidth and buffer resources

Research Goals Identification of proxy services o System research issues o , operating systems for proxies: resource allocation for Qo. S , middleware/interfaces for programmable services , network protocols: error recovery, prefetch/prefix caching, congestion control, service location/invocation o analysis, simulation, prototype and experiment

Sample Proxy Services patching o quality enhancement o transcoding o

Patching Service o problem , asynchronous requests for long video streams , low playback delay requirement o basic idea , client receives ongoing transmission from server , retrieves initial portion from proxy request video flow request

Multiple Clients Problem: multiple asynchronous requests for video o basic ideas o , batching, patching, segmented delivery, caching , schedule, multicast video segments over different multicast groups video flow

Quality Enhancement o problem , lossy, o time-varying bw path from server to proxy basic idea , proxy performs error recovery (ARQ, FEC) congestion control/buffering with server , simple clients see enhanced flow video data feedback enhanced video flow

Operating System Support o o flexible resource allocation mechanisms in proxy OS rate-based CPU, network, and disk schedulers , o o resource reservation mechanisms that provide performance guarantees to applications Storage management techniques for proxy workloads , o Challenge: design rate-based allocation mechanisms for large SMPs, disk arrays and multi-homed hosts Challenge: design techniques to handle workloads that frequently read, write and delete diverse objects from disk cache Platform: Use QLinux, a Qo. S-enhanced version of Linux that we have developed

Middleware/Interfaces: Pronto o programmable, active services separation of control, forwarding control: out of data path , best effort , asynchronous , o implementation: stream thinning, active congestion control , reliable mcast , traffic shaping , Meta control interface forwarding engine data path

Network Protocols Client/server/proxy o batching, patching, segmented delivery, catching protocols , , o data transfer: use of multiple multicast channels control, signaling Congestion control , , thinning, discard separate server-proxy, proxy-client “connections” Reliability enhancement: active repair services , FEC , time-critical error control ,

Current Status o server/client implementation , addition o of proxy, services QLinux: current version based on 2. 2. x kernel , rate-based CPU, packet, and disk schedulers PRONTO o partner with Z. Zhang (UMinn) o , distribution of software

Summary o Proxy services , enhanced performance , valued added services , proxy, clients “near” each other o System research issues , operating systems resource allocation for Qo. S , middleware for programmable services , network protocols o Analysis, simulation, prototype and experiment