A Hierarchical Characterization of a Live Streaming Media Workload

We present what we believe to be the first thorough characterization of live streaming media content delivered over the Internet. Our characterization of over five million requests spanning a 28-day period is done at three increasingly granular levels, corresponding to clients, sessions, and transfers. Our findings support two important conclusions. First, we show that the nature of interactions between users and objects is fundamentally different for live versus stored objects. Access to stored objects is user driven, whereas access to live objects is object driven. This reversal of active/passive roles of users and objects leads to interesting dualities. For instance, our analysis underscores a Zipf-like profile for user interest in a given object, which is to be contrasted to the classic Zipf-like popularity of objects for a given user. Also, our analysis reveals that transfer lengths are highly variable and that this variability is due to the stickiness of clients to a particular live object, as opposed to structural (size) properties of objects. Second, based on observations we make, we conjecture that the particular characteristics of live media access workloads are likely to be highly dependent on the nature of the live content being accessed. In our study, this dependence is clear from the strong temporal correlations we observed in the traces, which we attribute to the synchronizing impact of live content on access characteristics. Based on our analyses, we present a model for live media workload generation that incorporates many of our findings, and which we implement in GISMO [19].

Measuring the Behavior of a World-Wide Web Server

Server performance has become a crucial issue for improving the overall performance of the World-Wide Web. This paper describes Webmonitor, a tool for evaluating and understanding server performance, and presents new results for a realistic workload. Webmonitor measures activity and resource consumption, both within the kernel and in HTTP processes running in user space. Webmonitor is implemented using an efficient combination of sampling and event-driven techniques that exhibit low overhead. Our initial implementation is for the Apache World-Wide Web server running on the Linux operating system. We demonstrate the utility of Webmonitor by measuring and understanding the performance of a Pentium-based PC acting as a dedicated WWW server. Our workload uses a file size distribution with a heavy tail. This captures the fact that Web servers must concurrently handle some requests for large audio and video files, and a large number of requests for small documents, containing text or images. Our results show that in a Web server saturated by client requests, over 90% of the time spent handling HTTP requests is spent in the kernel. Furthermore, keeping TCP connections open, as required by TCP, causes a factor of 2-9 increase in the elapsed time required to service an HTTP request. Data gathered from Webmonitor provide insight into the causes of this performance penalty. Specifically, we observe a significant increase in resource consumption along three dimensions: the number of HTTP processes running at the same time, CPU utilization, and memory utilization. These results emphasize the important role of operating system and network protocol implementation in determining Web server performance.

Generating Representative Web Workloads for Network and Server Performance Evaluation

One role for workload generation is as a means for understanding how servers and networks respond to variation in load. This enables management and capacity planning based on current and projected usage. This paper applies a number of observations of Web server usage to create a realistic Web workload generation tool which mimics a set of real users accessing a server. The tool, called Surge (Scalable URL Reference Generator) generates references matching empirical measurements of 1) server file size distribution; 2) request size distribution; 3) relative file popularity; 4) embedded file references; 5) temporal locality of reference; and 6) idle periods of individual users. This paper reviews the essential elements required in the generation of a representative Web workload. It also addresses the technical challenges to satisfying this large set of simultaneous constraints on the properties of the reference stream, the solutions we adopted, and their associated accuracy. Finally, we present evidence that Surge exercises servers in a manner significantly different from other Web server benchmarks.

On the Interaction Between an Operating System and Web Server

This paper examines how and why web server performance changes as the workload at the server varies. We measure the performance of a PC acting as a standalone web server, running Apache on top of Linux. We use two important tools to understand what aspects of software architecture and implementation determine performance at the server. The first is a tool that we developed, called WebMonitor, which measures activity and resource consumption, both in the operating system and in the web server. The second is the kernel profiling facility distributed as part of Linux. We vary the workload at the server along two important dimensions: the number of clients concurrently accessing the server, and the size of the documents stored on the server. Our results quantify and show how more clients and larger files stress the web server and operating system in different and surprising ways. Our results also show the importance of fixed costs (i.e., opening and closing TCP connections, and updating the server log) in determining web server performance.

Task Assignment in a Distributed System: Improving Performance by Unbalancing Load

We consider the problem of task assignment in a distributed system (such as a distributed Web server) in which task sizes are drawn from a heavy-tailed distribution. Many task assignment algorithms are based on the heuristic that balancing the load at the server hosts will result in optimal performance. We show this conventional wisdom is less true when the task size distribution is heavy-tailed (as is the case for Web file sizes). We introduce a new task assignment policy, called Size Interval Task Assignment with Variable Load (SITA-V). SITA-V purposely operates the server hosts at different loads, and directs smaller tasks to the lighter-loaded hosts. The result is that SITA-V provably decreases the mean task slowdown by significant factors (up to 1000 or more) where the more heavy-tailed the workload, the greater the improvement factor. We evaluate the tradeoff between improvement in slowdown and increase in waiting time in a system using SITA-V, and show conditions under which SITA-V represents a particularly appealing policy. We conclude with a discussion of the use of SITA-V in a distributed Web server, and show that it is attractive because it has a simple implementation which requires no communication from the server hosts back to the task router.

Gismo: A Generator of Internet Streaming Media Objects and Workloads

This paper presents a tool called Gismo (Generator of Internet Streaming Media Objects and workloads). Gismo enables the specification of a number of streaming media access characteristics, including object popularity, temporal correlation of request, seasonal access patterns, user session durations, user interactivity times, and variable bit-rate (VBR) self-similarity and marginal distributions. The embodiment of these characteristics in Gismo enables the generation of realistic and scalable request streams for use in the benchmarking and comparative evaluation of Internet streaming media delivery techniques. To demonstrate the usefulness of Gismo, we present a case study that shows the importance of various workload characteristics in determining the effectiveness of proxy caching and server patching techniques in reducing bandwidth requirements.

Detour-Based Mobility Coordination in DTNs

Commonly, research work in routing for delay tolerant networks (DTN) assumes that node encounters are predestined, in the sense that they are the result of unknown, exogenous processes that control the mobility of these nodes. In this paper, we argue that for many applications such an assumption is too restrictive: while the spatio-temporal coordinates of the start and end points of a node's journey are determined by exogenous processes, the specific path that a node may take in space-time, and hence the set of nodes it may encounter could be controlled in such a way so as to improve the performance of DTN routing. To that end, we consider a setting in which each mobile node is governed by a schedule consisting of a ist of locations that the node must visit at particular times. Typically, such schedules exhibit some level of slack, which could be leveraged for DTN message delivery purposes. We define the Mobility Coordination Problem (MCP) for DTNs as follows: Given a set of nodes, each with its own schedule, and a set of messages to be exchanged between these nodes, devise a set of node encounters that minimize message delivery delays while satisfying all node schedules. The MCP for DTNs is general enough that it allows us to model and evaluate some of the existing DTN schemes, including data mules and message ferries. In this paper, we show that MCP for DTNs is NP-hard and propose two detour-based approaches to solve the problem. The first (DMD) is a centralized heuristic that leverages knowledge of the message workload to suggest specific detours to optimize message delivery. The second (DNE) is a distributed heuristic that is oblivious to the message workload, and which selects detours so as to maximize node encounters. We evaluate the performance of these detour-based approaches using extensive simulations based on synthetic workloads as well as real schedules obtained from taxi logs in a major metropolitan area. Our evaluation shows that our centralized, workload-aware DMD approach yields the best performance, in terms of message delay and delivery success ratio, and that our distributed, workload-oblivious DNE approach yields favorable performance when compared to approaches that require the use of data mules and message ferries.

Service Provisioning in Mobile Networks Through Distributed Coordinated Resource Management

The pervasiveness of personal computing platforms offers an unprecedented opportunity to deploy large-scale services that are distributed over wide physical spaces. Two major challenges face the deployment of such services: the often resource-limited nature of these platforms, and the necessity of preserving the autonomy of the owner of these devices. These challenges preclude using centralized control and preclude considering services that are subject to performance guarantees. To that end, this thesis advances a number of new distributed resource management techniques that are shown to be effective in such settings, focusing on two application domains: distributed Field Monitoring Applications (FMAs), and Message Delivery Applications (MDAs). In the context of FMA, this thesis presents two techniques that are well-suited to the fairly limited storage and power resources of autonomously mobile sensor nodes. The first technique relies on amorphous placement of sensory data through the use of novel storage management and sample diffusion techniques. The second approach relies on an information-theoretic framework to optimize local resource management decisions. Both approaches are proactive in that they aim to provide nodes with a view of the monitored field that reflects the characteristics of queries over that field, enabling them to handle more queries locally, and thus reduce communication overheads. Then, this thesis recognizes node mobility as a resource to be leveraged, and in that respect proposes novel mobility coordination techniques for FMAs and MDAs. Assuming that node mobility is governed by a spatio-temporal schedule featuring some slack, this thesis presents novel algorithms of various computational complexities to orchestrate the use of this slack to improve the performance of supported applications. The findings in this thesis, which are supported by analysis and extensive simulations, highlight the importance of two general design principles for distributed systems. First, a-priori knowledge (e.g., about the target phenomena of FMAs and/or the workload of either FMAs or DMAs) could be used effectively for local resource management. Second, judicious leverage and coordination of node mobility could lead to significant performance gains for distributed applications deployed over resource-impoverished infrastructures.

Hierarchal Characterization and Generation of Blogosphere Workloads

We present a thorough characterization of the access patterns in blogspace, which comprises a rich interconnected web of blog postings and comments by an increasingly prominent user community that collectively define what has become known as the blogosphere. Our characterization of over 35 million read, write, and management requests spanning a 28-day period is done at three different levels. The user view characterizes how individual users interact with blogosphere objects (blogs); the object view characterizes how individual blogs are accessed; the server view characterizes the aggregate access patterns of all users to all blogs. The more-interactive nature of the blogosphere leads to interesting traffic and communication patterns, which are different from those observed for traditional web content. We identify and characterize novel features of the blogosphere workload, and we show the similarities and differences between typical web server workloads and blogosphere server workloads. Finally, based on our main characterization results, we build a new synthetic blogosphere workload generator called GBLOT, which aims at mimicking closely a stream of requests originating from a population of blog users. Given the increasing share of blogspace traffic, realistic workload models and tools are important for capacity planning and traffic engineering purposes.

Improving the Accessibility of Lightweight Formal Verification Systems

In research areas involving mathematical rigor, there are numerous benefits to adopting a formal representation of models and arguments: reusability, automatic evaluation of examples, and verification of consistency and correctness. However, broad accessibility has not been a priority in the design of formal verification tools that can provide these benefits. We propose a few design criteria to address these issues: a simple, familiar, and conventional concrete syntax that is independent of any environment, application, or verification strategy, and the possibility of reducing workload and entry costs by employing features selectively. We demonstrate the feasibility of satisfying such criteria by presenting our own formal representation and verification system. Our system’s concrete syntax overlaps with English, LATEX and MediaWiki markup wherever possible, and its verifier relies on heuristic search techniques that make the formal authoring process more manageable and consistent with prevailing practices. We employ techniques and algorithms that ensure a simple, uniform, and flexible definition and design for the system, so that it easy to augment, extend, and improve.

Traffic Characteristics and Communication Patterns in Blogosphere

We present a thorough characterization of the access patterns in blogspace -- a fast-growing constituent of the content available through the Internet -- which comprises a rich interconnected web of blog postings and comments by an increasingly prominent user community that collectively define what has become known as the blogosphere. Our characterization of over 35 million read, write, and administrative requests spanning a 28-day period is done from three different blogosphere perspectives. The server view characterizes the aggregate access patterns of all users to all blogs; the user view characterizes how individual users interact with blogosphere objects (blogs); the object view characterizes how individual blogs are accessed. Our findings support two important conclusions. First, we show that the nature of interactions between users and objects is fundamentally different in blogspace than that observed in traditional web content. Access to objects in blogspace could be conceived as part of an interaction between an author and its readership. As we show in our work, such interactions range from one-to-many "broadcast-type" and many-to-one "registration-type" communication between an author and its readers, to multi-way, iterative "parlor-type" dialogues among members of an interest group. This more-interactive nature of the blogosphere leads to interesting traffic and communication patterns, which are different from those observed in traditional web content. Second, we identify and characterize novel features of the blogosphere workload, and we investigate the similarities and differences between typical web server workloads and blogosphere server workloads. Given the increasing share of blogspace traffic, understanding such differences is important for capacity planning and traffic engineering purposes, for example.