Enhancing Speedup in Network Processing Applications by Exploiting Instruction Reuse with Flow Aggregation

Instruction reuse is a microarchitectural technique that improves the execution time of a program by removing redundant computations at run-time. Although this is the job of an optimizing compiler, they do not succeed many a time due to limited knowledge of run-time data. In this paper we examine instruction reuse of integer ALU and load instructions in network processing applications. Specifically, this paper attempts to answer the following questions: (1) How much of instruction reuse is inherent in network processing applications?, (2) Can reuse be improved by reducing interference in the reuse buffer?, (3) What characteristics of network applications can be exploited to improve reuse?, and (4) What is the effect of reuse on resource contention and memory accesses? We propose an aggregation scheme that combines the high-level concept of network traffic i.e. "flows" with a low level microarchitectural feature of programs i.e. repetition of instructions and data along with an architecture that exploits temporal locality in incoming packet data to improve reuse. We find that for the benchmarks considered, 1% to 50% of instructions are reused while the speedup achieved varies between 1% and 24%. As a side effect, instruction reuse reduces memory traffic and can therefore be considered as a scheme for low power.

A probabilistic constrained nonlinear optimization framework to optimize RED parameters

The random early detection (RED) technique has seen a lot of research over the years. However, the functional relationship between RED performance and its parameters viz,, queue weight (omega(q)), marking probability (max(p)), minimum threshold (min(th)) and maximum threshold (max(th)) is not analytically availa ble. In this paper, we formulate a probabilistic constrained optimization problem by assuming a nonlinear relationship between the RED average queue length and its parameters. This problem involves all the RED parameters as the variables of the optimization problem. We use the barrier and the penalty function approaches for its Solution. However (as above), the exact functional relationship between the barrier and penalty objective functions and the optimization variable is not known, but noisy samples of these are available for different parameter values. Thus, for obtaining the gradient and Hessian of the objective, we use certain recently developed simultaneous perturbation stochastic approximation (SPSA) based estimates of these. We propose two four-timescale stochastic approximation algorithms based oil certain modified second-order SPSA updates for finding the optimum RED parameters. We present the results of detailed simulation experiments conducted over different network topologies and network/traffic conditions/settings, comparing the performance of Our algorithms with variants of RED and a few other well known adaptive queue management (AQM) techniques discussed in the literature.

QoS with selfish nodes in wireless networks

The IEEE 802.1le medium access control (MAC) standard provides distributed service differentiation or Quality-of- Service (QoS) by employing a priority system. In 802.1 le networks, network traffic is classified into different priorities or access categories (ACs). Nodes maintain separate queues for each AC and packets at the head-of-line (HOL) of each queue contend for channel access using AC-specific parameters. Such a mechanism allows the provision of differentiated QoS where high priority, performance sensitive traffic such as voice and video applications will enjoy less delay, greater throughput and smaller loss, compared to low priority traffic (e. g. file transfer). The standard implicitly assumes that nodes are honest and will truthfully classify incoming traffic into its appropriate AC. However, in the absence of any additional mechanism, selfish users can gain enhanced performance by selectively classifying low priority traffic as high priority, potentially destroying the QoS capability of the system.

An efficient web cache replacement policy

Several replacement policies for web caches have been proposed and studied extensively in the literature. Different replacement policies perform better in terms of (i) the number of objects found in the cache (cache hit), (ii) the network traffic avoided by fetching the referenced object from the cache, or (iii) the savings in response time. In this paper, we propose a simple and efficient replacement policy (hereafter known as SE) which improves all three performance measures. Trace-driven simulations were done to evaluate the performance of SE. We compare SE with two widely used and efficient replacement policies, namely Least Recently Used (LRU) and Least Unified Value (LUV) algorithms. Our results show that SE performs at least as well as, if not better than, both these replacement policies. Unlike various other replacement policies proposed in literature, our SE policy does not require parameter tuning or a-priori trace analysis and has an efficient and simple implementation that can be incorporated in any existing proxy server or web server with ease.

Mobile agent based node monitoring protocol for MANETs

Mobile ad-hoc network is a wireless ad-hoc network with dynamic network topology. The Dynamicity, due to the random node movement, and scarcity of resources lead to a challenge in monitoring the nodes in a MANET. Monitoring the lack of resources (bandwidth, buffer, and energy), misbehavior, and mobility at node level remains, a challenge. In a MANET the proposed protocol uses both static as well as mobile agents, where the mobile agents migrate to different clusters of the zones respectively, collect the node status information periodically, and provide a high level information to the static agent (which resides at the central node) by analyzing the raw information at the nodes. This, in turn, reduces the network traffic and conserves the workload of the central node, where a static agent is available with high level information and in coordination with other modules. The protocol has been tested in different size MANETs with variable number of nodes and applications. The results shown in the simulation indicates the effectiveness of the protocol.

Traffic Profiling for Efficient Network Resource Utilization.

Traffic Engineering has been the prime concern for Internet Service Providers (ISPs), with the main focus being minimization of over-utilization of network capacity even though additional capacity is available which is under-utilized, Furthermore, requirements of timely delivery of digitized audiovisual information raises a new challenge of finding a path meeting these requirements. This paper addresses the issue of (a) distributing load to achieve global efficiency in resource utilization. (b) Finding a path satisfying the real time requirements of, delay and bandwidth requested by the applications. In this paper we do a critical study of the link utilization that varies over time and determine the time interval during which the link occupancy remains constant across days. This information helps in pre-determining link utilization that is useful in balancing load in the network Finally, we run simulations that use a dynamic time interval for profiling traffic and show improvement in terms number of calls admitted/blocked.

Modeling Finite Buffer Effects on TCP Traffic over an IEEE 802.11 Infrastructure WLAN

The network scenario is that of an infrastructure IEEE 802.11 WLAN with a single AP with which several stations (STAs) are associated. The AP has a finite size buffer for storing packets. In this scenario, we consider TCP controlled upload and download file transfers between the STAs and a server on the wireline LAN (e.g., 100 Mbps Ethernet) to which the AP is connected. In such a situation, it is known (see, for example, (3), [9]) that because of packet loss due to finite buffers at the Ap, upload file transfers obtain larger throughputs than download transfers. We provide an analytical model for estimating the upload and download throughputs as a function of the buffer size at the AP. We provide models for the undelayed and delayed ACK cases for a TCP that performs loss recovery only by timeout, and also for TCP Reno.

Enhancing 'Mobility' through Integrated Transportation and Traffic Management

During the course of preparation of a master plan for the transportation networks in Bangalore city, mapping the various initiatives and interventions planned towards addressing mobility, existing situation and implications of some of the proposed interventions was analysed. The inferences are based on existing transportation network; synthesis of various transportation related studies and proposed infrastructure initiatives (road works) in Bangalore. Broadly, they can be summarized as following five aspects: I. Need for ~Sreclassifying~T existing road networks (arterial and sub-arterial) with effective geospatial database in the back-end. II. The proposed Core Ring Road at surface grade may not be feasible. III. Current interventions encouraging more independent motorable transport by way of road widening, construction of underpasses, flyovers and grade-separators would not ease traffic congestion when addressed in isolation. IV. Factors affecting time and cost-overruns in infrastructure projects and ways to tackle are discussed. V. Initiatives required for addressing effective planning for operations recommended.

Modeling finite buffer effects on TCP traffic over an IEEE 802.11 infrastructure WLAN

The network scenario is that of an infrastructure IEEE 802.11 WLAN with a single AP with which several stations (STAs) are associated. The AP has a finite size buffer for storing packets. In this scenario, we consider TCP-controlled upload and download file transfers between the STAs and a server on the wireline LAN (e.g., 100 Mbps Ethernet) to which the AP is connected. In such a situation, it is well known that because of packet losses due to finite buffers at the AP, upload file transfers obtain larger throughputs than download transfers. We provide an analytical model for estimating the upload and download throughputs as a function of the buffer size at the AP. We provide models for the undelayed and delayed ACK cases for a TCP that performs loss recovery only by timeout, and also for TCP Reno. The models are validated incomparison with NS2 simulations.

A Petri net model for evaluating packet buffering strategies in a network processor

Previous studies have shown that buffering packets in DRAM is a performance bottleneck. In order to understand the impediments in accessing the DRAM, we developed a detailed Petri net model of IP forwarding application on IXP2400 that models the different levels of the memory hierarchy. The cell based interface used to receive and transmit packets in a network processor leads to some small size DRAM accesses. Such narrow accesses to the DRAM expose the bank access latency, reducing the bandwidth that can be realized. With real traces up to 30% of the accesses are smaller than the cell size, resulting in 7.7% reduction in DRAM bandwidth. To overcome this problem, we propose buffering these small chunks of data in the on chip scratchpad memory. This scheme also exploits greater degree of parallelism between different levels of the memory hierarchy. Using real traces from the internet, we show that the transmit rate can be improved by an average of 21% over the base scheme without the use of additional hardware. Further, the impact of different traffic patterns on the network processor resources is studied. Under real traffic conditions, we show that the data bus which connects the off-chip packet buffer to the micro-engines, is the obstacle in achieving higher throughput.

The effect of traffic shaping in efficiently providing end-to-end performance guarantees

This paper reports new results concerning the capabilities of a family of service disciplines aimed at providing per-connection end-to-end delay (and throughput) guarantees in high-speed networks. This family consists of the class of rate-controlled service disciplines, in which traffic from a connection is reshaped to conform to specific traffic characteristics, at every hop on its path. When used together with a scheduling policy at each node, this reshaping enables the network to provide end-to-end delay guarantees to individual connections. The main advantages of this family of service disciplines are their implementation simplicity and flexibility. On the other hand, because the delay guarantees provided are based on summing worst case delays at each node, it has also been argued that the resulting bounds are very conservative which may more than offset the benefits. In particular, other service disciplines such as those based on Fair Queueing or Generalized Processor Sharing (GPS), have been shown to provide much tighter delay bounds. As a result, these disciplines, although more complex from an implementation point-of-view, have been considered for the purpose of providing end-to-end guarantees in high-speed networks. In this paper, we show that through ''proper'' selection of the reshaping to which we subject the traffic of a connection, the penalty incurred by computing end-to-end delay bounds based on worst cases at each node can be alleviated. Specifically, we show how rate-controlled service disciplines can be designed to outperform the Rate Proportional Processor Sharing (RPPS) service discipline. Based on these findings, we believe that rate-controlled service disciplines provide a very powerful and practical solution to the problem of providing end-to-end guarantees in high-speed networks.

Queuing strategies for qos management of traffic between lans interconnected by low-speed wan links

We provide a comparative performance evaluation of packet queuing and link admission strategies for low-speed wide area network Links (e.g. 9600 bps, 64 kbps) that interconnect relatively highspeed, connectionless local area networks (e.g. 10 Mbps). In particular, we are concerned with the problem of providing differential quality of service to interLAN remote terminal and file transfer sessions, and throughput fairness between interLAN file transfer sessions. We use analytical and simulation models to study a variety of strategies. Our work also serves to address the performance comparison of connectionless vs. connection-oriented interconnection of CLNS LANS. When provision of priority at the physical transmission level is not feasible, we show, for low-speed WAN links (e.g. 9600 bps), the superiority of connection-oriented interconnection of connectionless LANs, with segregation of traffic streams with different QoS requirements into different window flow controlled connections. Such an implementation can easily be obtained by transporting IP packets over an X.25 WAN. For 64 kbps WAN links, there is a drop in file transfer throughputs, owing to connection overheads, but the other advantages are retained, The same solution also helps to provide throughput fairness between interLAN file transfer sessions. We also provide a corroboration of some of our modelling results with results from an experimental test-bed.

Reinforcement Learning With Function Approximation for Traffic Signal Control

We propose, for the first time, a reinforcement learning (RL) algorithm with function approximation for traffic signal control. Our algorithm incorporates state-action features and is easily implementable in high-dimensional settings. Prior work, e. g., the work of Abdulhai et al., on the application of RL to traffic signal control requires full-state representations and cannot be implemented, even in moderate-sized road networks, because the computational complexity exponentially grows in the numbers of lanes and junctions. We tackle this problem of the curse of dimensionality by effectively using feature-based state representations that use a broad characterization of the level of congestion as low, medium, or high. One advantage of our algorithm is that, unlike prior work based on RL, it does not require precise information on queue lengths and elapsed times at each lane but instead works with the aforementioned described features. The number of features that our algorithm requires is linear to the number of signaled lanes, thereby leading to several orders of magnitude reduction in the computational complexity. We perform implementations of our algorithm on various settings and show performance comparisons with other algorithms in the literature, including the works of Abdulhai et al. and Cools et al., as well as the fixed-timing and the longest queue algorithms. For comparison, we also develop an RL algorithm that uses full-state representation and incorporates prioritization of traffic, unlike the work of Abdulhai et al. We observe that our algorithm outperforms all the other algorithms on all the road network settings that we consider.

Network Rhythms Influence the Relationship between Spike-Triggered Local Field Potential and Functional Connectivity

Characterizing the functional connectivity between neurons is key for understanding brain function. We recorded spikes and local field potentials (LFPs) from multielectrode arrays implanted in monkey visual cortex to test the hypotheses that spikes generated outward-traveling LFP waves and the strength of functional connectivity depended on stimulus contrast, as described recently. These hypotheses were proposed based on the observation that the latency of the peak negativity of the spike-triggered LFP average (STA) increased with distance between the spike and LFP electrodes, and the magnitude of the STA negativity and the distance over which it was observed decreased with increasing stimulus contrast. Detailed analysis of the shape of the STA, however, revealed contributions from two distinct sources-a transient negativity in the LFP locked to the spike (similar to 0 ms) that attenuated rapidly with distance, and a low-frequency rhythm with peak negativity similar to 25 ms after the spike that attenuated slowly with distance. The overall negative peak of the LFP, which combined both these components, shifted from similar to 0 to similar to 25 ms going from electrodes near the spike to electrodes far from the spike, giving an impression of a traveling wave, although the shift was fully explained by changing contributions from the two fixed components. The low-frequency rhythm was attenuated during stimulus presentations, decreasing the overall magnitude of the STA. These results highlight the importance of accounting for the network activity while using STAs to determine functional connectivity.

Reinforcement learning with average cost for adaptive control of traffic lights at intersections

We propose for the first time two reinforcement learning algorithms with function approximation for average cost adaptive control of traffic lights. One of these algorithms is a version of Q-learning with function approximation while the other is a policy gradient actor-critic algorithm that incorporates multi-timescale stochastic approximation. We show performance comparisons on various network settings of these algorithms with a range of fixed timing algorithms, as well as a Q-learning algorithm with full state representation that we also implement. We observe that whereas (as expected) on a two-junction corridor, the full state representation algorithm shows the best results, this algorithm is not implementable on larger road networks. The algorithm PG-AC-TLC that we propose is seen to show the best overall performance.