The recently emerging Converged Enhanced Ethernet (CEE) data center networks rely on layer-2 flow control in order to support packet loss sensitive transport protocols, such as RDMA and FCoE. Although lossless networks were proven to improve end-to-end network performance, without careful design and operation, they might suffer from in-network deadlocks, caused by cyclic buffer dependencies. These dependencies are called credit loops. Although existing credit loops rarely deadlock, when they do they can block large parts of the network. Naive solutions recover from credit loop deadlock by draining buffers and dropping packets. Previous works suggested credit-loop avoidance by central routing algorithms, but these assume specific topologies and are slow to react to failures.

In recent years, the demand for high-precision tracking systems has significantly increased in the field of Wireless Sensor Network (WSN). A new tracking system based on exploitation of Received Signal Strength Indicator (RSSI) measurements in WSN is proposed. The proposed system is designed in particular for WSNs that are deployed in close proximity and can transmit data at a high transmission rate. The close proximity and an optimized transmit power level enable accurate conversion of RSSI measurements to range estimates. Having an adequate transmission rate enables spatial-temporal correlation between consecutive RSSI measurements. In addition, advanced statistical and signal processing methods are used to mitigate channel distortion and to compensate for packet loss. The system is evaluated in indoor conditions and achieves tracking resolution of a few centimeters which is compatible with theoretical bounds.

In this paper we develop a continuous high-precision tracking system based on Received Signal Strength Indicator(RSSI) measurements for small ranges. The proposed system uses minimal number of sensor nodes with RSSI capabilities to track a moving object in close-proximity and high transmission rate. The close-proximity enables conversion of RSSI measurements to range estimates and the high transmission rate enables continuous tracking of the moving object. The RSSI-based tracking system includes calibration, range estimation, location estimation and refinement. We use advanced statistical and signal processing methods to mitigate channel distortion and packet loss. The system is evaluated in indoor settings and achieves tracking resolution of few centimeters. Therefore, it becomes the motion trackers of notice in many applications.

A security engine should detect network traffic attacks at line-speed. "Learning" capabilities can help detecting new and unknown threats even before a vulnerability is exploited. The principal way for achieving this goal is to model anticipated network traffic behavior, and to use this model for identifying anomalies. This paper focuses on denial of service (DoS) attacks and distributed DoS (DDoS). Our goal is detecting and preventing of attacks. The main challenges include minimizing the false-positive rate and the memory consumption. SPADE: a Statistical Packet Acceptance Defense Engine is presented. SPADE is an accurate engine that uses an hierarchical adaptive structure to detect suspicious traffic using a relatively small memory footprint, therefore can be easily applied on hardware. SPADE is based on the assumption that during DoS/DDoS attacks, a significant portion of the traffic that is seen belongs to the attack, therefore, SPADE applies a statistical mechanism to primarily filter the attack's traffic.

The constant race for faster and more powerful CPUs is drawing to a close. No longer is it feasible to significantly increase the speed of the CPU without paying a crushing penalty in power consumption and production costs. Instead of increasing single thread performance, the industry is turning to multiple CPU threads or cores (such as SMT and CMP) and heterogeneous CPU architectures (such as the Cell Broadband Engine). While this is a step in the right direction, in every modern PC there is a wealth of untapped compute resources. The NIC has a CPU; the disk controller is programmable; some high-end graphics adaptersare already more powerful than host CPUs. Some of these CPUs can perform some functions more efficiently than the host CPUs. Our operating systems and programming abstractions should be expanded to let applications tap into these computational resources and make the best use of them.

During the last two decades, a considerable amount of academic research has been conducted in the field of distributed computing. Typically, distributed applications require frequent network communication, which becomes a dominate factor in the overall runtime overhead. The recent proliferation of programmable peripheral devices for computer systems may be utilized in order to improve the performance of such applications. Offloading application-specific network functions to peripheral devices can improve performance and reduce host CPU utilization. Due to the peculiarities of each particular device and the difficulty of programming an outboard CPU, the need for an abstracted offloading framework is apparent. This paper proposes a novel offloading framework, called HYDRA that enables utilization of such devices. The framework enables an application developer to design the offloading aspects of the application by specifying an "offloading layout", which is enforced by the runtime during application deployment. The performance of a variety of distributed algorithms can be significantly improved by utilizing such a framework. We demonstrate this claim by evaluating several offloaded applications: a distributed total message ordering algorithm and a packet generator.

Many distributed systems may be limited in their performance by the number of transactions they are able to support per unit of time. In order to achieve fault tolerance and to boost a system's performance, active state machine replication is frequently used. It employs total ordering service to keep the state of replicas synchronized. In this paper, we present an architecture that enables a drastic increase in the number of ordered transactions in a cluster, using off-the-shelf network equipment. Performance supporting nearly one million ordered transactions per second has been achieved, which substantiates our claim.

The proliferation of programmable peripheral devices for computer systems opens new possibilities for academic research that will influence system designs in the near future. Programmability is a key feature that enables application-specific extensions to improve performance and offer new features. Increasing transistor density and decreasing cost provide excess computational power in devices such as disk controllers, network interfaces and video cards. This paper proposes an innovative programming model and runtime support that enables utilization of such devices by providing a generic code offloading framework. The framework enables an application developer to design the offloading aspects of the application by specifying an "offloading layout", which is enforced by the runtime during application deployment. The framework also provides the necessary development tools and programming constructs for developing such applications. We test our framework by implementing a packet generator on a programmable network card for network testing. The offloaded application produces traffic at five times the rate, and with inter-packet variability that is many orders of magnitude smaller than the non-offloaded version

Cooperative and reliable packet forwarding presents a formidable challenge in mobile ad hoc networks (MANET), due to special network characteristics; e.g., mobility, dynamic topology and absence of centralized management. Lack of cooperation, due to misbehavior caused by selfishness or malice, may severely degrade the performance of the network. Previous studies, relying on reputation systems, have demonstrated solutions designed for Dynamic Source Routing (DSR) protocol. This paper highlights various aspects of cooperation enforcement and reliability, when AODV is the underlying protocol. Furthermore, it presents a scalable protocol that combines a reputation system with AODV that addresses reputation fading, second-chance, robustness against liars and load balancing.

QoS-aware routing protocols have been the focus of much attention in the past decade. This is due to the interesting challenges posed by the problem of QoS routing, in the absence of precise information - or even partial and altogether imprecise information. We present a new QoS-aware routing protocol, OPsAR, which achieves very good performance results at a very reasonable cost, in terms of memory and messages, OPsAR is based on the multi-path routing approach, but constrains the number of paths used and leverages on previous resource reservation attempts. Every reservation attempt - successful or not - results in an update to the knowledge-state recorded at all the nodes that had participated in those attempts. This knowledge helps in avoiding network bottlenecks and coping with congested path when they are encountered. We present extensive simulation results and even compare ourselves favorably with a protocol that explores all possible paths.

The paper addresses the issue of TCP-friendly congestion control mechanism for many-to-many communication environment. Lack of congestion control inhibits deployment of WAN applications that involve collaboration of groups of processes in the Internet environment. Recent efforts targeted unicast WAN congestion control (TFRC). We extend that approach to multicast many-to-many applications that operate using a middleware framework. Our congestion control mechanism was implemented within a group communication middleware and tested in a multi-continent environment. The measurements have proved the proposed approach to be robust, efficient and TCP-friendly, as well as to provide fairness among processes that compete for shared resources.

This paper describes a highly available distributed video on demand (VoD) service which is inherently fault tolerant. The VoD service is provided by multiple servers that reside at different sites. New servers may be brought up "on the fly" to alleviate the load on other servers. When a server crashes it is replaced by another server in a transparent way; the clients are unaware of the change of service provider. In test runs of our VoD service prototype, such transitions are not noticeable to a human observer who uses the service. Our VoD service uses a sophisticated flow control mechanism and supports adjustment of the video quality to client capabilities. It does not assume any proprietary network technology: it uses commodity hardware and publicly available network technologies (e.g., TCP/IP, ATM). Our service may run on any machine connected to the Internet. The service exploits a group communication system as a building block for high availability. The utilization of group communication greatly simplifies the service design.