Srikanth Sundaresan

Community contribution award -- Measuring and mitigating web performance bottlenecks in broadband access networks

We measure Web performance bottlenecks in home broadband access networks and evaluate ways to mitigate these bottlenecks with caching within home networks. We first measure Web performance bottlenecks to nine popular Web sites from more than 5,000 broadband access networks and demonstrate that when the downstream throughput of the access link exceeds about 16 Mbits/s, latency is the main bottleneck for Web page load time. Next, we use a router-based Web measurement tool, Mirage, to deconstruct Web page load time into its constituent components (DNS lookup, TCP connection setup, object download) and show that simple latency optimizations can yield significant improvements in overall page load times. We then present a case for placing a cache in the home network and deploy three common optimizations: DNS caching, TCP connection caching, and content caching. We show that caching only DNS and TCP connections yields significant improvements in page load time, even when the users browser is already performing similar independent optimizations. Finally, we use traces from real homes to demonstrate how prefetching DNS and TCP connections for popular sites in a home-router cache can achieve faster page load times.

Measuring broadband performance in South Africa

Broadband penetration is increasing in South Africa, particularly on mobile devices, but little is known about the performance of fixed or mobile broadband in the country. This lack of empirical data imposes significant limitations to innovation, because broadband performance metrics help users audit their connectivity costs and regulators to make informed decisions about policies and infrastructure investments. We present the results from a measurement study of both fixed and mobile broadband connections in South Africa. We use measurement software that we implemented on mobile phones and home routers and adapted to address challenges that are unique to the developing world. Our findings suggest that consumers in South Africa are not getting advertised speeds, that mobile broadband generally has higher throughput than fixed broadband, and that interconnection between ISPs (or lack thereof) plays a significant role in determining the reliability and performance that users ultimately receive. Often, high latencies to destinations introduce significant performance bottlenecks, suggesting that, in addition to investments in higher throughput links, effort should be devoted to improving interconnection between ISPs and locating content closer to users. Our study, along with our open source technical platform, embodies an archetypal method for monitoring broadband performance in developing countries.

Peeking behind the NAT: an empirical study of home networks

We present the first empirical study of home network availability, infrastructure, and usage, using data collected from home networks around the world. In each home, we deploy a router with custom firmware to collect information about the availability of home broadband network connectivity, the home network infrastructure (including the wireless connectivity in each home network and the number of devices connected to the network), and how people in each home network use the network. Downtime is more frequent and longer in developing countries---sometimes due to the network, and in other cases because they simply turn their home router off. We also find that some portions of the wireless spectrum are extremely crowded, that diurnal patterns are more pronounced during the week, and that most traffic in home networks is exchanged over a few connections to a small number of domains. Our study is both a preliminary view into many home networks and an illustration of how measurements from a home router can yield significant information about home networks.

Measuring home broadband performance

We present the results from the first study of Internet access link performance measured directly from home routers. In conjunction with the Federal Communication Commissions study of broadband Internet access in the United States, we investigate the throughput and latency of network access links from about 4000 routers across eight ISPs. Our findings provide a snapshot of access network performance across the United States, offer insights on how access network performance should be measured and presented to users, and inform various ongoing efforts to evaluate the performance of access networks around the world.

Beyond the Radio: Illuminating the Higher Layers of Mobile Networks

Cellular network performance is often viewed as primarily dominated by the radio technology. However, reality proves more complex: mobile operators deploy and configure their networks in different ways, and sometimes establish network sharing agreements with other mobile carriers. Moreover, regulators have encouraged newer operational models such as Mobile Virtual Network Operators (MVNOs) to promote competition. In this paper we draw upon data collected by the ICSI Netalyzr app for Android to characterize how operational decisions, such as network configurations, business models, and relationships between operators introduce diversity in service quality and affect user security and privacy. We delve in detail beyond the radio link and into network configuration and business relationships in six countries. We identify the widespread use of transparent middleboxes such as HTTP and DNS proxies, analyzing how they actively modify user traffic, compromise user privacy, and potentially undermine user security. In addition, we identify network sharing agreements between operators, highlighting the implications of roaming and characterizing the properties of MVNOs, including that a majority are simply rebranded versions of major operators. More broadly, our findings highlight the importance of considering higher-layer relationships when seeking to analyze mobile traffic in a sound fashion.

Measuring the Performance of User Traffic in Home Wireless Networks

This paper studies how home wireless performance characteristics affect the performance of user traffic in real homes. Previous studies have focused either on wireless metrics exclusively, without connection to the performance of user traffic; or on the performance of the home network at higher layers. In contrast, we deploy a passive measurement tool on commodity access points to correlate wireless performance metrics with TCP performance of user traffic. We implement our measurement tool, deploy it on commodity routers in 66 homes for one month, and study the relationship between wireless metrics and TCP performance of user traffic. We find that, most of the time, TCP flows from devices in the home achieve only a small fraction of available access link throughput; as the throughput of user traffic approaches the access link throughput, the characteristics of the home wireless network more directly affect performance. We also find that the 5 GHz band offers users better performance better than the 2.4 GHz band, and although the performance of devices varies within the same home, many homes do not have multiple devices sending high traffic volumes, implying that certain types of wireless contention may be uncommon in practice.

Home Network or Access Link? Locating Last-Mile Downstream Throughput Bottlenecks

As home networks see increasingly faster downstream throughput speeds, a natural question is whether users are benefiting from these faster speeds or simply facing performance bottlenecks in their own home networks. In this paper, we ask whether downstream throughput bottlenecks occur more frequently in their home networks or in their access ISPs. We identify lightweight metrics that can accurately identify whether a throughput bottleneck lies inside or outside a user’s home network and develop a detection algorithm that locates these bottlenecks. We validate this algorithm in controlled settings and report on two deployments, one of which included 2,652 homes across the United States. We find that wireless bottlenecks are more common than access-link bottlenecks—particularly for home networks with downstream throughput greater than 20 Mbps, where access-link bottlenecks are relatively rare.

Header Enrichment or ISP Enrichment?: Emerging Privacy Threats in Mobile Networks

HTTP header enrichment allows mobile operators to annotate HTTP connections via the use of a wide range of request headers. Operators employ proxies to introduce such headers for operational purposes, and---as recently widely publicized---also to assist advertising programs in identifying the subscriber responsible for the originating traffic, with significant consequences for the users privacy. In this paper, we use data collected by the Netalyzr network troubleshooting service over 16 months to identify and characterize HTTP header enrichment in modern mobile networks. We present a timeline of HTTP header usage for 299 mobile service providers from 112 countries, observing three main categories: (1) unique user and device identifiers (e.g., IMEI and IMSI), (2) headers related to advertising programs, and (3) headers associated with network operations.

Accelerating last-mile web performance with popularity-based prefetching

As broadband speeds increase, latency is becoming a bottleneck for many applications—especially for Web downloads. Latency affects many aspects ofWeb page load time, from DNS lookups to the time to complete a three-way TCP handshake; it also contributes to the time it takes to transfer the Web objects for a page. Previous work has shown that much of this latency can occur in the last mile [2]. Although some performance bottlenecks can be mitigated by increasing downstream throughput (e.g., by purchasing a higher service plan), in many cases, latency introduces performance bottlenecks, particularly for connections with higher throughput. To mitigate latency bottlenecks in the last mile, we have implemented a system that performs DNS prefetching and TCP connection caching to the Web sites that devices inside a home visit most frequently, a technique we call popularity-based prefetching. Many devices and applications already perform DNS prefetching and maintain persistent TCP connections, but most prefetching is predictive based on the content of the page, rather than on past site popularity. We evaluate the optimizations using a simulator that we drive from traffic traces that we collected from five homes in the BISmark testbed [1]. We find that performing DNS prefetching and TCP connection caching for the twenty most popular sites inside the home can double DNS and connection cache hit rates.

Locating throughput bottlenecks in home networks

We present a demonstration of WTF (Wheres The Fault?), a system that localizes performance problems in home and access networks. We implement WTF as custom firmware that runs in an off-the-shelf home router. WTF uses timing and buffering information from passively monitored traffic at home routers to detect both access link and wireless network bottlenecks.