Crowdsourced Live Streaming (CLS), most notably Twitch.tv, has seen explosive growth in its popularity in the past few years. In such systems, any user can lively broadcast video content of interest to others, e.g., from a game player to many online viewers. To fulfill the demands from both massive and heterogeneous broadcasters and viewers, expensive server clusters have been deployed to provide video ingesting and transcoding services. Despite the existence of highly popular channels, a significant portion of the channels is indeed unpopular. Yet as our measurement shows, these broadcasters are consuming considerable system resources; in particular, 25% (resp. 30%) of bandwidth (resp. computation) resources are used by the broadcasters who do not have any viewers at all. In this paper, we closely examine the challenge of handling unpopular live-broadcasting channels in CLS systems and present a comprehensive solution for service partitioning on hybrid cloud. The trace-driven evaluation shows that our hybrid cloud-assisted design can smartly assign ingesting and transcoding tasks to the elastic cloud virtual machines, providing flexible system deployment cost-effectively.
|Original language||English (US)|
|Title of host publication||Proceedings of the 26th International Workshop on Network and Operating Systems Support for Digital Audio and Video, NOSSDAV 2016|
|Publisher||Association for Computing Machinery, Inc|
|Number of pages||6|
|State||Published - May 10 2016|
|Event||26th ACM Workshop on Network and Operating Systems Support for Digital Audio and Video, NOSSDAV 2016 - Klagenfurt, Austria|
Duration: May 13 2016 → …
|Name||Proceedings of the 26th International Workshop on Network and Operating Systems Support for Digital Audio and Video, NOSSDAV 2016|
|Other||26th ACM Workshop on Network and Operating Systems Support for Digital Audio and Video, NOSSDAV 2016|
|Period||5/13/16 → …|
Bibliographical noteFunding Information:
This research is supported by an NSERC Discovery Grant, NSERC RTI Grant and NSERC Strategic Grant. C. Zhang' s work is supported in part by a China Scholarship Council (CSC) Scholarship Program. H. Wang's work was supported by Chancellor's Small Grant and Grant-in-aid programs from the University of Minnesota.
© 2016 ACM.
Copyright 2016 Elsevier B.V., All rights reserved.
- Crowdsourced live streaming
- Hybrid cloud
- Workload migration