K. K. Ramakrishnan

Eliminating receive livelock in an interrupt-driven kernel

Most operating systems use interface interrupts to schedule network tasks. Interrupt-driven systems can provide low overhead and good latency at low offered load, but degrade significantly at higher arrival rates unless care is taken to prevent several pathologies. These are various forms ofreceive livelock, in which the system spends all of its time processing interrupts, to the exclusion of other necessary tasks. Under extreme conditions, no packets are delivered to the user application or the output of the system. To avoid livelock and related problems, an operating system must schedule network interrupt handling as carefully as it schedules process execution. We modified an interrupt-driven networking implementation to do so; this modification eliminates receive livelock without degrading other aspects of system performance. Our modifications include the use of polling when the system is heavily loaded, while retaining the use of interrupts ur.Jer lighter load. We present measurements demonstrating the success of our approach.

A binary feedback scheme for congestion avoidance in computer networks

We propose a scheme for congestion avoidance in networks using a connectionless protocol at the network layer. The scheme uses a minimal amount of feedback from the network to the users, who adjust the amount of traffic allowed into the network. The routers in the network detect congestion and set a congestion-indication bit on packets flowing in the forward direction. The congestion indication is communicated back to the users through the transport-level acknowledgment. The scheme is distributed, adapts to the dynamic state of the network, converges to the optimal operating point, is quite simple to implement, and has low overhead. The scheme maintains fairness in service provided to multiple sources. This paper presents the scheme and the analysis that went into the choice of the various decision mechanisms. We also address the performance of the scheme under transient changes in the network and pathological overload conditions.

Design and Characterization of a Full-Duplex Multiantenna System for WiFi Networks

In this paper, we present an experiment- and simulation-based study to evaluate the use of full duplex (FD) as a potential mode in practical IEEE 802.11 networks. To enable the study, we designed a 20-MHz multiantenna orthogonal frequency-division-multiplexing (OFDM) FD physical layer and an FD media access control (MAC) protocol, which is backward compatible with current 802.11. Our extensive over-the-air experiments, simulations, and analysis demonstrate the following two results. First, the use of multiple antennas at the physical layer leads to a higher ergodic throughput than its hardware-equivalent multiantenna half-duplex (HD) counterparts for SNRs above the median SNR encountered in practical WiFi deployments. Second, the proposed MAC translates the physical layer rate gain into near doubling of throughput for multinode single-AP networks. The two results allow us to conclude that there are potentially significant benefits gained from including an FD mode in future WiFi standards.

A binary feedback scheme for congestion avoidance in computer networks with a connectionless network layer

We propose a scheme for congestion avoidance in networksusing a connectionless protocol at the network layer. The schemeuses feedback from the network to the users of the network. Theinteresting challenge for the scheme is to use a minimal amount offeedback (one bit in each packet) from the network to adjust theamount of traffic allowed into the network. The servers in thenetwork detect congestion and set a congestion indicationbit on packets flowing in the forward direction. The congestionindication is communicated back to the users through the transportlevel acknowledgement.The scheme is distributed, adapts to the dynamic state of thenetwork, converges to the optimal operating point, is quite simpleto implement, and has low overhead while operational. The schemealso addresses a very important aspect of fairness in theservice provided to the various sources utilizing the network. Thescheme attempts to maintain fairness in service provided tomultiple sources. This paper presents the scheme and the analysis that went intothe choice of the various decision mechanisms. We also address theperformance of the scheme under transient changes in the networkand for pathological conditions.

Resource management with hoses: point-to-cloud services for virtual private networks

As IP technologies providing both tremendous capacity and the ability to establish dynamic security associations between endpoints emerge, virtual private networks (VPNs) are going through dramatic growth. The number of endpoints per VPN is growing and the communication pattern between endpoints is becoming increasingly hard to predict. Consequently, users are demanding dependable, dynamic connectivity between endpoints, with the network expected to accommodate any traffic matrix, as long as the traffic to the endpoints does not overwhelm the capacity of the respective ingress and egress links. We propose a new service interface, termed a hose, to provide the appropriate performance abstraction. A hose is characterized by the aggregate traffic to and from one endpoint in the VPN to a set of other endpoints in the VPN, and by an associated performance guarantee.Hoses provide important advantages to a VPN customer: 1) flexibility to send traffic to a set of endpoints without having to specify the detailed traffic matrix, and 2) reduction in the size of access links through multiplexing gains obtained from the natural aggregation of the flows between endpoints. As compared with the conventional point-to-point (or customer pipe) model for managing quality of service (QoS), hoses provide reduction in the state information a customer must maintain. On the other hand, hoses would appear to increase the complexity of the already difficult problem of resource management to support QoS. To manage network resources in the face of this increased uncertainty, we consider both conventional statistical multiplexing techniques, and a new resizing technique based on online measurements.To study these performance issues, we run trace-driven simulations, using traffic derived from AT&Ts voice network and from a large corporate data network. From the customers perspective, we find that aggregation of traffic at the hose level provides significant multiplexing gains. From the providers perspective, we find that the statistical multiplexing and resizing techniques deal effectively with uncertainties about the traffic, providing significant gains over the conventional alternative of a mesh of statically sized customer pipes between endpoints.

Optimal content placement for a large-scale VoD system

IPTV service providers offering Video-on-Demand currently use servers at each metropolitan office to store all the videos in their library. With the rapid increase in library sizes, it will soon become infeasible to replicate the entire library at each office. We present an approach for intelligent content placement that scales to large library sizes (e.g., 100 Ks of videos). We formulate the problem as a mixed integer program (MIP) that takes into account constraints such as disk space, link bandwidth, and content popularity. To overcome the challenges of scale, we employ a Lagrangian relaxation-based decomposition technique combined with integer rounding. Our technique finds a near-optimal solution (e.g., within 1%-2%) with orders of magnitude speedup relative to solving even the linear programming (LP) relaxation via standard software. We also present simple strategies to address practical issues such as popularity estimation, content updates, short-term popularity fluctuation, and frequency of placement updates. Using traces from an operational system, we show that our approach significantly outperforms simpler placement strategies. For instance, our MIP-based solution can serve all requests using only half the link bandwidth used by least recently used (LRU) or least frequently used (LFU) cache replacement policies. We also investigate the tradeoff between disk space and network bandwidth.

NetVM: High Performance and Flexible Networking Using Virtualization on Commodity Platforms

NetVM brings virtualization to the Network by enabling high bandwidth network functions to operate at near line speed, while taking advantage of the flexibility and customization of low cost commodity servers. NetVM allows customizable data plane processing capabilities such as firewalls, proxies, and routers to be embedded within virtual machines, complementing the control plane capabilities of Software Defined Networking. NetVM makes it easy to dynamically scale, deploy, and reprogram network functions. This provides far greater flexibility than existing purpose-built, sometimes proprietary hardware, while still allowing complex policies and full packet inspection to determine subsequent processing. It does so with dramatically higher throughput than existing software router platforms. NetVM is built on top of the KVM platform and Intel DPDK library. We detail many of the challenges we have solved such as adding support for high-speed inter-VM communication through shared huge pages and enhancing the CPU scheduler to prevent overheads caused by inter-core communication and context switching. NetVM allows true zero-copy delivery of data to VMs both for packet processing and messaging among VMs within a trust boundary. Our evaluation shows how NetVM can compose complex network functionality from multiple pipelined VMs and still obtain throughputs up to 10 Gbps, an improvement of more than 250% compared to existing techniques that use SR-IOV for virtualized networking.

Congestion avoidance in computer networks with a connectionless network layer: concepts, goals and methodology

Widespread use of computer networks and the use of varied technology for the interconnection of computers has made congestion a signi cant problem. In this report, we summarize our research on congestion avoidance. We compare the concept of congestion avoidance with that of congestion control. Brie y, congestion control is a recovery mechanism, while congestion avoidance is a prevention mechanism. A congestion control scheme helps the network to recover from the congestion state while a congestion avoidance scheme allows a network to operate in the region of low delay and high throughput with minimal queuing, thereby preventing it from entering the congested state in which packets are lost due to bu er shortage. A number of possible alternatives for congestion avoidance were identi ed. From these alternatives we selected one called the binary feedback scheme in which the network uses a single bit in the network layer header to feed back the congestion information to its users, which then increase or decrease their load to make optimal use of the resources. The concept of global optimality in a distributed system is de ned in terms of e ciency and fairness such that they can be independently quanti ed and apply to any number of resources and users. The proposed scheme has been simulated and shown to be globally e cient, fair, responsive, convergent, robust, distributed, and con guration-independent.

Explicit window adaptation: a method to enhance TCP performance

We study the performance of TCP in an internetwork consisting of both rate-controlled and nonrate-controlled segments. A common example of such an environment occurs when the end systems are part of IP datagram networks interconnected by a rate-controlled segment, such as an ATM network using the available bit rate (ABR) service. In the absence of congestive losses in either segment, TCP keeps increasing its window to its maximum size. Mismatch between the TCP window and the bandwidth-delay product of the network will result in accumulation of large queues and possibly buffer overflows in the devices at the edges of the rate-controlled segment, causing degraded throughput and unfairness. We develop an explicit feedback scheme, called Explicit Window Adaptation, based on modifying the receivers advertised window in TCP acknowledgments returning to the source. The window size indicated to TCP is a function of the free buffer in the edge device. Results from simulations with a wide range of traffic scenarios show that this explicit window adaptation scheme can control the buffer occupancy efficiently at the edge device, and results in significant improvements in packet loss rate, fairness, and throughput over a packet discard policy such as Random Early Detection (RED).

An efficient rate allocation algorithm for ATM networks providing max-min fairness

We describe a new algorithm for rate allocation within the individual switches of an ATM network implementing a rate-based congestion control algorithm for Available Bit-Rate (ABR) traffic. The algorithm performs an allocation in Θ(1) time, allowing it to be applied to ATM switches supporting a large number of virtual circuits. When the total available capacity or the requests of the individual connections change, the algorithm converges to the max-min allocation. Results from simulations using ATM sources show that the algorithm provides close to ideal throughput and converges to the max-min fair allocation rapidly when the available bandwidth or the individual requests change.