Performance Characterization of a Commercial Video Streaming Service

Abstract

Despite the growing popularity of video streaming over the Internet, problems such as re-buffering and high startup latency continue to plague users. In this paper, we present an end-to-end characterization of Yahoo's video streaming service, analyzing over 500 million video chunks downloaded over a two-week period. We gain unique visibility into the causes of performance degradation by instrumenting both the CDN server and the client player at the chunk level, while also collecting frequent snapshots of TCP variables from the server network stack. We uncover a range of performance issues, including an asynchronous disk-read timer and cache misses at the server, high latency and latency variability in the network, and buffering delays and dropped frames at the client. Looking across chunks in the same session, or destined to the same IP prefix, we see how some performance problems are relatively persistent, depending on the video's popularity, the distance between the client and server, and the client's operating system, browser, and Flash runtime.

Benchmarking Video Service Quality: Quantifying the Viewer Impact of Loss-Related Impairments

“…We obtain the following values:d (0,10] = −36.0%, d (10,20] = −41.9%,d (20,30] = −36.1%,d (30,40] = −31.2%.…”

“…Focused on VoD content delivered from an Akamai Content Delivery Network (CDN), the investigation in [29] concludes that fewer content chunks are viewed on lossy sessions overall with early loss being particularly detrimental to engagement. Using CDN-delivered VoD sessions, [30] propose a method to demarcate correlation and causation. The authors use a customer matching algorithm to design quasi-experiments from data that identifies causal links between start-up delay and session abandonment by connection strength, rebuffering ratio and viewing duration, and video failure to start and low likelihood of viewer to return to platform.…”

Understanding Video Streaming Algorithms in the Wild

“…YouTube itself is relatively well studied, with several analyses of various aspects of its behavior [16,5,27], including video encoding, startup behavior, bandwidth variations at fixed quality, a test similar to our reactivity analysis, variation of segment lengths, and redownloads to replace already fetched segments. There is also an end-end analysis of Yahoo's video streaming platform using data from the provider [8]. Several comparisons and analysis of academic ABR algorithms [29,26,24] have also been published, including within each of the several new proposals mentioned above.…”

Understanding Video Management Planes

“…Failure Triaging. Troubleshooting video performance problems is challenging, and poor performance may be due to a CDN, the network or the user's device [62,67], or a combination of these factors [67]. In addition, performance problems may be associated with a particular streaming protocol (e.g., manifest files may have errors for specific protocols).…”

“…This body of work has studied several aspects, including 1) architecture, serving strategy and its evolution, 2) characterization of videos in terms of encoded bitrates, total number of videos, popularity, caching, and 3) the user access patterns and quality of experience etc. Ghasemi et al [62] conducted an in-depth study of Yahoo's video serving infrastructure to reveal problems in different points in the video delivery pipeline. Other work has also examined different types of video services including a Pay-TV [44], cellular video [58], an on-demand service [70] and user-generated live streaming services [75,78].…”