Kartik Gopalan

Centralized channel assignment and routing algorithms for multi-channel wireless mesh networks

The IEEE 802.11 Wireless LAN standards allow multiple non-overlapping frequency channels to be used simultaneously to increase the aggregate bandwidth available to end-users. Such bandwidth aggregation capability is routinely used in infrastructure mode operation, where the traffic to and from wireless nodes is distributed among multiple interfaces of an access point or among multiple access points to balance the traffic load. However, bandwidth aggregation is rarely used in the context of multi-hop 802.11-based LANs that operate in the ad hoc mode. Most past research efforts that attempt to exploit multiple radio channels require modifications to the MAC protocol and therefore do not work with commodity 802.11 interface hardware. In this paper, we propose and evaluate one of the first multi-channel multi-hop wireless ad-hoc network architectures that can be built using standard 802.11 hardware by equipping each node with multiple network interface cards (NICs) operating on different channels. We focus our attention on wireless mesh networks that serve as the backbone for relaying end-user traffic from wireless access points to the wired network. The idea of exploiting multiple channels is particularly appealing in wireless mesh networks because of their high capacity requirements to support backbone traffic. To reap the full performance potential of this architecture, we develop a set of centralized channel assignment, bandwidth allocation, and routing algorithms for multi-channel wireless mesh networks. A detailed performance evaluation shows that with intelligent channel and bandwidth assignment, equipping every wireless mesh network node with just 2 NICs operating on different channels can increase the total network goodput by a factor of up to 8 compared with the conventional single-channel ad hoc network architecture.

Viking: a multi-spanning-tree Ethernet architecture for metropolitan area and cluster networks

Simplicity, cost effectiveness, scalability, and the economies of scale make Ethernet a popular choice for local area networks, as well as for storage area networks and increasingly metropolitan-area networks. These applications of Ethernet elevate it from a LAN technology to a ubiquitous networking technology, thus prompting a rethinking of some of its architectural features. One weakness of existing Ethernet architecture is its use of single spanning tree, which, while useful at avoiding routing loops, leads to low link utilization and long failure recovery time. To apply Ethernet to cluster networks and MANs, these problems need to be addressed. We propose a multi-spanning-tree Ethernet architecture, called Viking, that improves both aggregate throughput and fault tolerance by exploiting standard virtual LAN technology in a novel way. By supporting multiple spanning trees through VLAN, Viking makes the most of the inherent redundancies in most mesh-like networks and delivers a multi-fold throughput gain over single-spanning-tree Ethernet with the same physical network topology. It also provides much faster failure recovery, reducing the down-time to a sub-second range from that of multiple seconds in single-spanning-tree Ethernet architecture. Finally, based only on standard mechanisms, Viking is readily implementable on commodity Ethernet switches without any firmware modifications.

XenLoop: a transparent high performance inter-vm network loopback

Advances in virtualization technology have focused mainly on strengthening the isolation barrier between virtual machines (VMs) that are co-resident within a single physical machine. At the same time, a large category of communication intensive distributed applications and software components exist, such as web services, high performance grid applications, transaction processing, and graphics rendering, that often wish to communicate across this isolation barrier with other endpoints on co-resident VMs. State of the art inter-VM communication mechanisms do not adequately address the requirements of such applications. TCP/UDP based network communication tends to perform poorly when used between co-resident VMs, but has the advantage of being transparent to user applications. Other solutions exploit inter-domain shared memory mechanisms to improve communication latency and bandwidth, but require applications or user libraries to be rewritten against customized APIs - something not practical for a large majority of distributed applications. In this paper, we present the design and implementation of a fully transparent and high performance inter-VM network loopback channel, called XenLoop, in the Xen virtual machine environment. XenLoop does not sacrifice user-level transparency and yet achieves high communication performance between co-resident guest VMs. XenLoop intercepts outgoing network packets beneath the network layer and shepherds the packets destined to co-resident VMs through a high-speed inter-VM shared memory channel that bypasses the virtualized network interface. Guest VMs using XenLoop can migrate transparently across machines without disrupting ongoing network communications, and seamlessly switch between the standard network path and the XenLoop channel. In our evaluation using a number of unmodified benchmarks, we observe that XenLoop can reduce the inter-VM round trip latency by up to a factor of 5 and increase bandwidth by a up to a factor of 6.

Gang Migration of Virtual Machines Using Cluster-wide Deduplication

Gang migration refers to the simultaneous live migration of multiple Virtual Machines (VMs) from one set of physical machines to another in response to events such as load spikes and imminent failures. Gang migration generates a large volume of network traffic and can overload the core network links and switches in a data center. In this paper, we present an approach to reduce the network overhead of gang migration using global deduplication (GMGD). GMGD identifies and eliminates the retransmission of duplicate memory pages among VMs running on multiple physical machines in the cluster. We describe the design, implementation and evaluation of a GMGD prototype using QEMU/KVM VMs. Evaluations on a 30-node Gigabit Ethernet cluster having 10GigE core links shows that GMGD can reduce the network traffic on core links by up to 65% and the total migration time of VMs by up to 42% when compared to the default migration technique in QEMU/KVM. Furthermore, GMGD has a smaller adverse performance impact on network-bound applications.

Modeling vanet deployment in urban settings

The growing interest in wireless Vehicular Ad Hoc Networks (VANETs) has prompted greater research into simulation models that better reflect urban VANET deployments. Still, we lack a systematic understanding of the required level of simulation details in modeling various real-world urban constraints. In this work, we developed a series of simulation models that account for street layout, traffic rules, multilane roads, acceleration-deceleration, and RF attenuation due to obstacles. Using real and controlled synthetic maps, we evaluated the sensitivity of the simulation results toward these details. Our results indicate that the delivery ratio and packet delays in VANETs are more sensitive to the clustering effect of vehicles at intersections and their acceleration/deceleration. The VANET performance appears to be only marginally affected by the simulation of multiple lanes and careful synchronization at traffic signals. We also found that the performance in dense VANETs improves significantly when routing decisions are limited to a wireless backbone of mesh nodes, whereas in sparse VANETs, performance improves when vehicles also participate in ad hoc routing. Finally, through measurement and analysis of signal strengths around urban city blocks, we show that the effect of signal attenuation due to physical obstacles can potentially be parameterized in simulations. Our work provides a starting point for further understanding and development of more accurate VANET simulation model.

MemX: Virtualization of Cluster-Wide Memory

We present MemX -- a distributed system that virtualizes cluster-wide memory to support data-intensive and large memory workloads in virtual machines (VMs). MemX provides a number of benefits in virtualized settings: (1) VM workloads that access large datasets can perform low-latency I/O over virtualized cluster-wide memory; (2) VMs can transparently execute very large memory applications that require more memory than physical DRAM present in the host machine; (3) MemX reduces the effective memory usage of the cluster by de-duplicating pages that have identical content; (4) existing applications do not require any modifications to benefit from MemX such as the use of special APIs, libraries, recompilation, or relinking; and (5) MemX supports live migration of large-footprint VMs by eliminating the need to migrate part of their memory footprint resident on other nodes. Detailed evaluations of our MemX prototype show that large dataset applications and multiple concurrent VMs achieve significant performance improvements using MemX compared against virtualized local and iSCSI disks.

Load balancing routing with bandwidth-delay guarantees

The current generation of network carriers competes intensely to satisfy the diverse wide-area connectivity requirements of customers. At the same time, the carriers inherently wish to maximize the usage efficiency of their network infrastructure. Much of the research in network resource management has been devoted to providing bandwidth guarantees and preventing network congestion. However, the rapid growth in number and diversity of real-time network applications has made it imperative to consider the impact of end-to-end delay of traffic requirements on network resource provisioning. We present an efficient network resource provisioning algorithm, called link criticality based routing (LCBR), which relies on the guiding theme that load balancing leads to higher resource utilization efficiency. LCBR applies a simple but very effective notion of link criticality to achieve networkwide load balance while simultaneously meeting the QoS requirements of bandwidth and end-to-end delay. In addition, LCBR can simultaneously provision both primary and backup routes to support fast recovery from node or link failures. This article reviews the state of the art in network resource provisioning with QoS guarantees, introduces the LCBR algorithm, and identifies future research challenges.

Implementation experiences of bandwidth guarantee on a wireless LAN

Rether was originally developed to support guaranteed Quality of Service (QoS) for shared Ethernet LANs. With the growing popularity of wireless LANs, we modified the Rether protocol to provide QoS guarantee on wireless networks. In this paper, we present the design and implementation of the Wireless Rether protocol for 802.11 networks. We also describe our experiences with wireless LAN hardware. Wireless Rether supports QoS for TCP and UDP traffic in both upstream and downstream directions. The protocol can seamlessly inter-operate with any priority-based QoS mechanisms (such as Diffserv on the wired networks that connect the wireless access network to the rest of the Internet. QoS requirements of real-time applications are specified as a simple configurable policy table. Legacy networking applications can benefit from QoS guarantees provided by Wireless Rether without requiring any modifications.

Probabilistic delay guarantees using delay distribution measurement

Carriers increasingly differentiate their wide-area connectivity offerings by means of customized services, such as virtual private networks (VPN) with Quality of Service (QoS) guarantees, or QVPNs. The key challenge faced by carriers is to maximize the number of QVPNs admitted by exploiting the statistical multiplexing nature of input traffic. While existing measurement-based admission control algorithms utilize statistical multiplexing along the bandwidth dimension, they do not satisfactorily exploit statistical multiplexing along the <i>delay dimension</i> to guarantee <i>distinct per-QVPN delay bounds</i>. This paper presents Delay Distribution Measurement (DDM) based admission control algorithm, the first measurement-based approach that effectively exploits statistical multiplexing along the delay dimension. In other words, DDM exploits the well known fact that the actual delay experienced by most packets of a QVPN is usually far smaller than its worst-case delay bound requirement since multiple QVPNs rarely send traffic bursts at the same time. Additionally, DDM supports QVPNs with distinct probabilistic delay guarantees -- QVPNs that can tolerate more delay violations can reserve fewer resource than those that tolerate less, even though they require the same delay bound. A comprehensive performance evaluation using Voice over IP traces shows that, when compared to deterministic admission control, DDM can potentially increase the number of admitted QVPNs (and link utilization) by up to a factor of 3.0 even when the delay violation probability is as small as 10^-5.

DMTP: Controlling spam through message delivery differentiation

Unsolicited commercial email, commonly known as spam, has become a pressing problem in todays Internet. In this paper, we re-examine the architectural foundations of the current email delivery system that are responsible for the proliferation of email spam. We argue that the difficulties in controlling spam stem from the fact that the current email system is fundamentally sender-driven and distinctly lacks receiver control over email delivery. Based on these observations we propose a Differentiated Mail Transfer Protocol (DMTP), which grants receivers greater control over how messages from different senders should be delivered on the Internet. In addition, we also develop a simple mathematical model to study the effectiveness of DMTP in controlling spam. Through numerical experiments we demonstrate that DMTP can effectively reduce the maximum revenue that a spammer can gather. Moreover, compared to the current SMTP-based email system, the proposed email system can force spammers to stay online for longer periods of time, which may significantly improve the performance of various real-time blacklists of spammers. In addition, DMTP provides an incremental deployment path from the current SMTP-based system in todays Internet.