Safe Compositional Specification of Networking Systems

The Science of Network Service Composition has clearly emerged as one of the grand themes driving many of our research questions in the networking field today [NeXtworking 2003]. This driving force stems from the rise of sophisticated applications and new networking paradigms. By "service composition" we mean that the performance and correctness properties local to the various constituent components of a service can be readily composed into global (end-to-end) properties without re-analyzing any of the constituent components in isolation, or as part of the whole composite service. The set of laws that would govern such composition is what will constitute that new science of composition. The combined heterogeneity and dynamic open nature of network systems makes composition quite challenging, and thus programming network services has been largely inaccessible to the average user. We identify (and outline) a research agenda in which we aim to develop a specification language that is expressive enough to describe different components of a network service, and that will include type hierarchies inspired by type systems in general programming languages that enable the safe composition of software components. We envision this new science of composition to be built upon several theories (e.g., control theory, game theory, network calculus, percolation theory, economics, queuing theory). In essence, different theories may provide different languages by which certain properties of system components can be expressed and composed into larger systems. We then seek to lift these lower-level specifications to a higher level by abstracting away details that are irrelevant for safe composition at the higher level, thus making theories scalable and useful to the average user. In this paper we focus on services built upon an overlay management architecture, and we use control theory and QoS theory as example theories from which we lift up compositional specifications.

Collocation Games and Their Application to Distributed Resource Management

We introduce Collocation Games as the basis of a general framework for modeling, analyzing, and facilitating the interactions between the various stakeholders in distributed systems in general, and in cloud computing environments in particular. Cloud computing enables fixed-capacity (processing, communication, and storage) resources to be offered by infrastructure providers as commodities for sale at a fixed cost in an open marketplace to independent, rational parties (players) interested in setting up their own applications over the Internet. Virtualization technologies enable the partitioning of such fixed-capacity resources so as to allow each player to dynamically acquire appropriate fractions of the resources for unencumbered use. In such a paradigm, the resource management problem reduces to that of partitioning the entire set of applications (players) into subsets, each of which is assigned to fixed-capacity cloud resources. If the infrastructure and the various applications are under a single administrative domain, this partitioning reduces to an optimization problem whose objective is to minimize the overall deployment cost. In a marketplace, in which the infrastructure provider is interested in maximizing its own profit, and in which each player is interested in minimizing its own cost, it should be evident that a global optimization is precisely the wrong framework. Rather, in this paper we use a game-theoretic framework in which the assignment of players to fixed-capacity resources is the outcome of a strategic "Collocation Game". Although we show that determining the existence of an equilibrium for collocation games in general is NP-hard, we present a number of simplified, practically-motivated variants of the collocation game for which we establish convergence to a Nash Equilibrium, and for which we derive convergence and price of anarchy bounds. In addition to these analytical results, we present an experimental evaluation of implementations of some of these variants for cloud infrastructures consisting of a collection of multidimensional resources of homogeneous or heterogeneous capacities. Experimental results using trace-driven simulations and synthetically generated datasets corroborate our analytical results and also illustrate how collocation games offer a feasible distributed resource management alternative for autonomic/self-organizing systems, in which the adoption of a global optimization approach (centralized or distributed) would be neither practical nor justifiable.

Distributed Packet Rewriting and its Application to Scalable Server Architectures

To construct high performance Web servers, system builders are increasingly turning to distributed designs. An important challenge that arises in distributed Web servers is the need to direct incoming connections to individual hosts. Previous methods for connection routing have employed a centralized node which handles all incoming requests. In contrast, we propose a distributed approach, called Distributed Packet Rewriting (DPR), in which all hosts of the distributed system participate in connection routing. We argue that this approach promises better scalability and fault-tolerance than the centralized approach. We describe our implementation of four variants of DPR and compare their performance. We show that DPR provides performance comparable to centralized alternatives, measured in terms of throughput and delay under the SPECweb96 benchmark. Finally, we argue that DPR is particularly attractive both for small scale systems and for systems following the emerging trend toward increasingly intelligent I/O subsystems.