Aditya Akella

Network traffic characteristics of data centers in the wild

Although there is tremendous interest in designing improved networks for data centers, very little is known about the network-level traffic characteristics of data centers today. In this paper, we conduct an empirical study of the network traffic in 10 data centers belonging to three different categories, including university, enterprise campus, and cloud data centers. Our definition of cloud data centers includes not only data centers employed by large online service providers offering Internet-facing applications but also data centers used to host data-intensive (MapReduce style) applications). We collect and analyze SNMP statistics, topology and packet-level traces. We examine the range of applications deployed in these data centers and their placement, the flow-level and packet-level transmission properties of these applications, and their impact on network and link utilizations, congestion and packet drops. We describe the implications of the observed traffic patterns for data center internal traffic engineering as well as for recently proposed architectures for data center networks.

Self-management in chaotic wireless deployments

Over the past few years, wireless networking technologies have made vast forays into our daily lives. Today, one can find 802.11 hardware and other personal wireless technology employed at homes, shopping malls, coffee shops and airports. Present-day wireless network deployments bear two important properties: they are unplanned, with most access points (APs) deployed by users in a spontaneous manner, resulting in highly variable AP densities; and they are unmanaged, since manually configuring and managing a wireless network is very complicated. We refer to such wireless deployments as being chaotic.In this paper, we present a study of the impact of interference in chaotic 802.11 deployments on end-client performance. First, using large-scale measurement data from several cities, we show that it is not uncommon to have tens of APs deployed in close proximity of each other. Moreover, most APs are not configured to minimize interference with their neighbors. We then perform trace-driven simulations to show that the performance of end-clients could suffer significantly in chaotic deployments. We argue that end-client experience could be significantly improved by making chaotic wireless networks self-managing. We design and evaluate automated power control and rate adaptation algorithms to minimize interference among neighboring APs, while ensuring robust end-client performance.

MicroTE: fine grained traffic engineering for data centers

The effects of data center traffic characteristics on data center traffic engineering is not well understood. In particular, it is unclear how existing traffic engineering techniques perform under various traffic patterns, namely how do the computed routes differ from the optimal routes. Our study reveals that existing traffic engineering techniques perform 15% to 20% worse than the optimal solution. We find that these techniques suffer mainly due to their inability to utilize global knowledge about flow characteristics and make coordinated decision for scheduling flows. To this end, we have developed MicroTE, a system that adapts to traffic variations by leveraging the short term and partial predictability of the traffic matrix. We implement MicroTE within the OpenFlow framework and with minor modification to the end hosts. In our evaluations, we show that our system performs close to the optimal solution and imposes minimal overhead on the network making it appropriate for current and future data centers.

OpenNF: enabling innovation in network function control

Network functions virtualization (NFV) together with software-defined networking (SDN) has the potential to help operators satisfy tight service level agreements, accurately monitor and manipulate network traffic, and minimize operating expenses. However, in scenarios that require packet processing to be redistributed across a collection of network function (NF) instances, simultaneously achieving all three goals requires a framework that provides efficient, coordinated control of both internal NF state and network forwarding state. To this end, we design a control plane called OpenNF. We use carefully designed APIs and a clever combination of events and forwarding updates to address race conditions, bound overhead, and accommodate a variety of NFs. Our evaluation shows that OpenNF offers efficient state control without compromising flexibility, and requires modest additions to NFs.

An empirical evaluation of wide-area internet bottlenecks

Performance limitations in the current Internet are thought to lie at the edges of the network -- i.e last mile connectivity to users, or access links of stub ASes. As these links are upgraded, however, it is important to consider where new bottlenecks and hot-spots are likely to arise. Through an extensive measurement study, we discover, classify and characterize non-access bottleneck links in terms of their location, latency and available capacity. We find that nearly half of the paths explored have a non-access bottleneck with available capacity less than 50 Mbps. The bottlenecks identified are roughly equally split between intra-ISP links and links between ISPs. These results have implications on issues such as the choice of access providers and route optimization.

CloudNaaS: a cloud networking platform for enterprise applications

Enterprises today face several challenges when hosting line-of-business applications in the cloud. Central to many of these challenges is the limited support for control over cloud network functions, such as, the ability to ensure security, performance guarantees or isolation, and to flexibly interpose middleboxes in application deployments. In this paper, we present the design and implementation of a novel cloud networking system called CloudNaaS. Customers can leverage CloudNaaS to deploy applications augmented with a rich and extensible set of network functions such as virtual network isolation, custom addressing, service differentiation, and flexible interposition of various middleboxes. CloudNaaS primitives are directly implemented within the cloud infrastructure itself using high-speed programmable network elements, making CloudNaaS highly efficient. We evaluate an OpenFlow-based prototype of CloudNaaS and find that it can be used to instantiate a variety of network functions in the cloud, and that its performance is robust even in the face of large numbers of provisioned services and link/device failures.

Redundancy in network traffic: findings and implications

A large amount of popular content is transferred repeatedly across network links in the Internet. In recent years, protocol-independent redundancy elimination, which can remove duplicate strings from within arbitrary network flows, has emerged as a powerful technique to improve the efficiency of network links in the face of repeated data. Many vendors offer such redundancy elimination middleboxes to improve the effective bandwidth of enterprise, data center and ISP links alike. In this paper, we conduct a large scale trace-driven study of protocol independent redundancy elimination mechanisms, driven by several terabytes of packet payload traces collected at 12 distinct network locations, including the access link of a large US-based university and of 11 enterprise networks of different sizes. Based on extensive analysis, we present a number of findings on the benefits and fundamental design issues in redundancy elimination systems. Two of our key findings are (1) A new redundancy elimination algorithm based on Winnowing that outperforms the widely-used Rabin fingerprint-based algorithm by 5-10% on most traces and by as much as 35% in some traces. (2) A surprising finding that 75-90% of middleboxs bandwidth savings in our enterprise traces is due to redundant byte-strings from within each clients traffic, implying that pushing redundancy elimination capability to the end hosts, i.e. an end-to-end redundancy elimination solution, could obtain most of the middleboxs bandwidth savings.

SmartRE: an architecture for coordinated network-wide redundancy elimination

Application-independent Redundancy Elimination (RE), or identifying and removing repeated content from network transfers, has been used with great success for improving network performance on enterprise access links. Recently, there is growing interest for supporting RE as a network-wide service. Such a network-wide RE service benefits ISPs by reducing link loads and increasing the effective network capacity to better accommodate the increasing number of bandwidth-intensive applications. Further, a networkwide RE service democratizes the benefits of RE to all end-to-end traffic and improves application performance by increasing throughput and reducing latencies. While the vision of a network-wide RE service is appealing, realizing it in practice is challenging. In particular, extending single vantage-point RE solutions designed for enterprise access links to the network-wide case is inefficient and/or requires modifying routing policies. We present SmartRE, a practical and efficient architecture for network-wide RE. We show that SmartRE can enable more effective utilization of the available resources at network devices, and thus can magnify the overall benefits of network-wide RE. We prototype our algorithms using Click and test our framework extensively using several real and synthetic traces.

A comparison of overlay routing and multihoming route control

The limitations of BGP routing in the Internet are often blamed for poor end-to-end performance and prolonged connectivity interruptions. Recent work advocates using overlays to effectively bypass BGPs path selection in order to improve performance and fault tolerance. In this paper, we explore the possibility that intelligent control of BGP routes, coupled with ISP multihoming, can provide competitive end-to-end performance and reliability. Using extensive measurements of paths between nodes in a large content distribution network, we compare the relative benefits of overlay routing and multihoming route control in terms of round-trip latency, TCP connection throughput, and path availability. We observe that the performance achieved by route control together with multihoming to three ISPs (3-multihoming), is within 5-15% of overlay routing employed in conjunction 3-multihoming, in terms of both end-to-end RTT and throughput. We also show that while multihoming cannot offer the nearly perfect resilience of overlays, it can eliminate almost all failures experienced by a singly-homed end-network. Our results demonstrate that, by leveraging the capability of multihoming route control, it is not necessary to circumvent BGP routing to extract good wide-area performance and availability from the existing routing system.

Understanding data center traffic characteristics

As data centers become more and more central in Internet communications, both research and operations communities have begun to explore how to better design and manage them. In this paper, we present a preliminary empirical study of end-to-end traffic patterns in data center networks that can inform and help evaluate research and operational approaches. We analyze SNMP logs collected at 19 data centers to examine temporal and spatial variations in link loads and losses. We find that while links in the core are heavily utilized the ones closer to the edge observe a greater degree of loss. We then study packet traces collected at a small number of switches in one data center and find evidence of ON-OFF traffic behavior. Finally, we develop a framework that derives ON-OFF traffic parameters for data center traffic sources that best explain the SNMP data collected for the data center. We show that the framework can be used to evaluate data center traffic engineering approaches. We are also applying the framework to design network-level traffic generators for data centers.