Karthik Lakshminarayanan

Load Balancing in Structured P2P Systems

Most P2P systems that provide a DHT abstraction distribute objects among “peer nodes” by choosing random identifiers for the objects. This could result in an O(log N) imbalance. Besides, P2P systems can be highly heterogeneous, i.e. they may consist of peers that range from old desktops behind modem lines to powerful servers connected to the Internet through high-bandwidth lines. In this paper, we address the problem of load balancing in such P2P systems. We explore the space of designing load-balancing algorithms that uses the notion of “virtual servers”. We present three schemes that differ primarily in the amount of information used to decide how to re-arrange load. Our simulation results show that even the simplest scheme is able to balance the load within 80% of the optimal value, while the most complex scheme is able to balance the load within 95% of the optimal value.

ROFL: routing on flat labels

It is accepted wisdom that the current Internet architecture conflates network locations and host identities, but there is no agreement on how a future architecture should distinguish the two. One could sidestep this quandary by routing directly on host identities themselves, and eliminating the need for network-layer protocols to include any mention of network location. The key to achieving this is the ability to route on flat labels. In this paper we take an initial stab at this challenge, proposing and analyzing our ROFL routing algorithm. While its scaling and efficiency properties are far from ideal, our results suggest that the idea of routing on flat labels cannot be immediately dismissed.

A layered naming architecture for the internet

Currently the Internet has only one level of name resolution, DNS, which converts user-level domain names into IP addresses. In this paper we borrow liberally from the literature to argue that there should be three levels of name resolution: from user-level descriptors to service identifiers; from service identifiers to endpoint identifiers; and from endpoint identifiers to IP addresses. These additional levels of naming and resolution (1) allow services and data to be first class Internet objects (in that they can be directly and persistently named), (2) seamlessly accommodate mobility and multi-homing and (3) integrate middleboxes (such as NATs and firewalls) into the Internet architecture. We further argue that flat names are a natural choice for the service and endpoint identifiers. Hence, this architecture requires scalable resolution of flat names, a capability that distributed hash tables (DHTs) can provide.

Bandwidth estimation in broadband access networks

There has been much work on developing techniques for estimating the capacity and the available bandwidth of network paths based on end-point measurements. The focus has primarily been on settings where the constrained link can be modeled as a point-to-point link with a well-defined bandwidth, serving packets in FIFO order. In this paper, we point out that broadband access networks, such as cable modem and 802.11-based wireless networks, break this model in various ways. The constrained link could (a) employ mechanisms such as token bucket rate regulation, (b) schedule packets in a non-FIFO manner, and (c) support multiple distinct rates. We study how these characteristics impede the operation of the various existing methods and tools for capacity and available bandwidth estimation, and present a new available bandwidth estimation technique, <i>Probe- Gap</i>, that overcomes some of these difficulties. Our evaluation is based on experiments with actual 802.11a and cable modem links.

Achieving convergence-free routing using failure-carrying packets

Current distributed routing paradigms (such as link-state, distance-vector, and path-vector) involve a convergence process consisting of an iterative exploration of intermediate routes triggered by certain events such as link failures. The convergence process increases router load, introduces outages and transient loops, and slows reaction to failures. We propose a new routing paradigm where the goal is not to reduce the convergence times but rather to eliminate the convergence process completely. To this end, we propose a technique called Failure-Carrying Packets (FCP) that allows data packets to autonomously discover a working path without requiring completely up-to-date state in routers. Our simulations, performed using real-world failure traces and Rocketfuel topologies, show that: (a) the overhead of FCP is very low, (b) unlike traditional link-state routing (such as OSPF), FCP can provide both low loss-rate as well as low control overhead, (c) compared to prior work in backup path pre-computations, FCP provides better routing guarantees under failures despite maintaining lesser state at the routers.

Taming IP packet flooding attacks

One of the major problems faced by Internet hosts is denialof-service (DoS) caused by IP packet floods. Hosts in the Internet are unable to stop packets addressed to them. Once a host’s network link becomes congested, IP routers respond to the overload by dropping packets arbitrarily. This is contrary to the goals of the host, which could respond more effectively to overload if it had control over which packets were dropped. For example, a host may reject new connections rather than accept excess load. A host running multiple services may give higher priority to some services than others (service differentiation). Also, a host may provide lower quality service rather than reject requests (service degradation).

Support for service composition in i3

We consider the problem of service composition in a wide area network, where an end-user can send its packets through intermediate processing points (middleboxes) which can perform a variety of services. Example of such services are filtering, intrusion detection, anonymization, transcoding, and caching. In this paper, we argue that the Internet Indirection Infrastructure (i3)--an overlay network architecture that enables users to locate services and control the path followed by their packets--provides a natural platform for service composition. We discuss the challenges in implementing service compositions on top of i3, and suggest several approaches to address these challenges.

End-host controlled multicast routing

The last decade has seen a deluge of proposals for supporting multicast in the Internet. These proposals can be categorized as either infrastructure-based, with the multicast functionality provided by specialized network nodes, or host-based, with the multicast functionality provided by the members of the multicast group itself. In this paper, we present the design and evaluation of a hybrid multicast architecture wherein the infrastructure provides packet forwarding, and the end-hosts implement the control plane. End-hosts build multicast trees by setting up forwarding state in the infrastructure. This division of functionality enables our architecture to combine the efficiency of infrastructure-based solutions and the flexibility and deployability of host-based solutions. We present scalable and efficient algorithms for distributed tree construction and maintenance, and for reliable packet delivery. We have implemented the algorithms using i3 as the forwarding infrastructure. We evaluate our techniques using a combination of event-driven packet-level simulations, and our implementation over the PlanetLab testbed.

Brief announcement: towards a secure indirection infrastructure

Designing a flexible, yet secure communication infrastructure has long been an elusive goal. Most of the proposals that seek to address the problem of flexibility have opened up the system for new forms of attacks. In this paper, we consider one particular proposal, i3 [2], a flexible indirection infrastructure that provides natural support for a multitude of communication primitives such as multicast, anycast and mobility. We systematically identify the attacks on i3, and propose techniques that address the security problems without sacrificing the flexibility that i3 offers. Our techniques, ranging from cryptographically constraining the forwarding entries to challenge-based mechanisms for inserting forwarding entries, while being simple, both conceptually and to implement, make most of the attacks provably hard. We believe that this paper represents an important step towards designing communication infrastructures that are both secure and flexible.

Securing user-controlled routing infrastructures

Designing infrastructures that give untrusted third parties (such as end-hosts) control over routing is a promising research direction for achieving flexible and efficient communication. However, serious concerns remain over the deployment of such infrastructures, particularly the new security vulnerabilities they introduce. The flexible control plane of these infrastructures can be exploited to launch many types of powerful attacks with little effort. In this paper, we make several contributions towards studying security issues in forwarding infrastructures (FIs). We present a general model for an FI, analyze potential security vulnerabilities, and present techniques to address these vulnerabilities. The main technique that we introduce in this paper is the use of simple lightweight cryptographic constraints on forwarding entries. We show that it is possible to prevent a large class of attacks on end-hosts and bound the flooding attacks that can be launched on the infrastructure nodes to a small constant value. Our mechanisms are general and apply to a variety of earlier proposals such as i3, DataRouter, and Network Pointers.