Improving the performance of passive network monitoring applications with memory locality enhancements

Passive network monitoring is the basis for a multitude of systems that support the robust, efficient, and secure operation of modern computer networks. Emerging network monitoring applications are more demanding in terms of memory and CPU resources due to the increasingly complex analysis operations that are performed on the inspected traffic. At the same time, as the traffic throughput in modern network links increases, the CPU time that can be devoted for processing each network packet decreases. This leads to a growing demand for more efficient passive network monitoring systems in which runtime performance becomes a critical issue.In this paper we present locality buffering, a novel approach for improving the runtime performance of a large class of CPU and memory intensive passive monitoring applications, such as intrusion detection systems, traffic characterization applications, and NetFlow export probes. Using locality buffering, captured packets are being reordered by clustering packets with the same port number before they are delivered to the monitoring application. This results in improved code and data locality, and consequently, in an overall increase in the packet processing throughput and decrease in the packet loss rate. We have implemented locality buffering within the widely used libpcap packet capturing library, which allows existing monitoring applications to transparently benefit from the reordered packet stream without modifications. Our experimental evaluation shows that locality buffering improves significantly the performance of popular applications, such as the Snort IDS, which exhibits a 21% increase in the packet processing throughput and is able to handle 67% higher traffic rates without dropping any packets.     

Entropy maximisation and open queueing networks with priorities and blocking

A review is carried out on the characterisation and algorithmic implementation of an extended product-form approximation, based on the principle of maximum entropy (ME), for a wide class of arbitrary finite capacity open queueing network models (QNMs) with service and space priorities. A single server finite capacity GE/GE/1/N queue with R (R>1) distinct priority classes, compound Poisson arrival processes (CPPs) with geometrically distributed batches and generalised exponential (GE) service times is analysed via entropy maximisation, subject to suitable GE-type queueing theoretic constraints, under preemptive resume (PR) and head-of-line (HOL) scheduling rules combined with complete buffer sharing (CBS) and partial buffer sharing (PBS) management schemes stipulating a sequence of buffer thresholds {N=(N₁,…,N_R),0<N_i≤N_i−1,i=2,…,R}. The GE/GE/1/N queue is utilised, in conjunction with GE-type first two moment flow approximation formulae, as a cost-effective building block towards the establishment of a generic ME queue-by-queue decomposition algorithm for arbitrary open QNMs with space and service priorities under repetitive service blocking with random destination (RS-RD). Typical numerical results are included to illustrate the credibility of the ME algorithm against simulation for various network topologies and define experimentally pessimistic GE-type performance bounds. Remarks on the extensions of the ME algorithm to other types of blocking mechanisms, such as repetitive service blocking with fixed destination (RS-FD) and blocking-after-service (BAS), are included.     

Fluorouracil and leucovorin with or without interferon alfa-2b in advanced colorectal cancer: analysis of a prospective randomized phase III trial. Hellenic Cooperative Oncology Group

PURPOSE: To investigate if double modulation of fluorouracil (5-FU) with leucovorin (folinic acid [FA]) and interferon alfa-2b (IFN 2b) improves responses and survival in comparison to single modulation of 5-FU with FA. PATIENTS AND METHODS: One hundred six patients with histologically confirmed advanced colorectal cancer, measurable disease, and without previous chemotherapy were prospectively randomized into two groups. Patients in group A received 5-FU 450 mg/m2 as an intravenous bolus in the midinfusion of FA weekly. FA was given at a dose of 200 mg/m2 in 500 mL 0.9% normal saline solution in 2-hour infusion. Patients in group B received exactly the same regimen plus IFN 2b 5 million units subcutaneously three times weekly. RESULTS: All patients were well balanced in both groups regarding age, sex, performance status, number, and site of metastasis. One hundred two patients were assessable. All patients have died. There was no difference in response between the two groups (7.8% v 9.8%). Median survival was 10.1 months in group A, and 7.2 months in group B (P = .00189). Median time to progression was 8.4 and 5.2 months, respectively (P = .00196). Overall, better performance status and older age had a positive impact on survival. Toxicity was the most important and catastrophic aspect of this study. Patients who received IFN 2b had significantly worse anemia, neutropenia, diarrhea, anorexia, weight loss, flu-like syndrome, and psychological reactions. CONCLUSION: Based on this final analysis, the addition of IFN 2b to the combination of 5-FU and FA enhances toxicity and contributes to decreased survival.     

Thin element applications of a new formulation for C structural elements

A new formulation was proposed recently for the removal of the shear and membrane locking mechanisms from the finite element equations of the structural C⁰ shell, plate and beam elements. The use of full integration with the proposed formulation does not allow development of the zero energy modes or the softening effects, usually associated with the use of the technique of reduced integration in C⁰ plate and shell element applications. In the present paper a beneficial side effect of the new formulation is presented with regard to the development of the purely machine dependent locking. Questions concerning the introduction of softening effects by the new formulation in some flat C⁰ plate/shell element applications are addressed.     

MRE hierarchical decomposition of general queueing network models

Summary The principle of Minimum Relative Entropy (MRE), given fully decomposable subset and aggregate mean queue length, utilisation and flow-balance constraints, is used in conjunction with asymptotic connections to infinite capacity queues, to derive new analytic approximations for the conditional and marginal state probabilities of single class general closed queueing network models (QNMs) in the context of a multilevel variable aggregation scheme. The concept of subparallelism is applied to preserve the flow conservation and a universal MRE hierarchical decomposition algorithm is proposed for the approximate analysis of arbitrary closed queueing networks with single server queues and general service-times. Heuristic criteria towards an optimal coupling of network's units at each level of aggregation are suggested. As an illustration, the MRE algorithm is implemented iteratively by using the Generalised Exponential (GE) distributional model to approximate the service and asymptotic flow processes in the network. This algorithm captures the exact solution of separable queueing networks, while for general queueing networks it compares favourably against exact solutions and known approximations.This work is sponsored by the Science and Engineering Research Council (SERC), UK, under grant GR/F29271     

The moment redistribution effect of the C0 structural elements formulation

A new formulation was proposed recently for the removal of the shear and membrane locking mechanisms from the C⁰ structural elements. The performance of the new formulation was shown to be excellent in many cases of beam, plate and shell element applications, completely eliminating all locking problems. However, this formulation has its own problems. The potential introduction of softening effects (yielding softer models) and a rotational zero energy mode describe the problematic behaviour of the new formulation in cases of C⁰ plate and shell element applications. Analysis of this behaviour reveals some interesting aspects of the classical finite element formulation and allows for a better insight into the overall behaviour of the C⁰ structural elements. As a result of the present analysis, a modification of new formulation, remedying its problematic behaviour, will appear soon.     

Testing the asymptotic behaviour of shell elements—Part I: the classical benchmark tests

The asymptotic behaviour is considered to be one of the most demanding levels of benchmark testing for shell elements. In the present paper, the asymptotic behaviour of classical benchmark problems is analytically and numerically investigated. The aim is to examine the possibility of using the classical benchmark tests for testing the asymptotic behaviour of shell elements. Appropriate analytical approaches are introduced to investigate the asymptotic behaviour of the classical benchmark problems. The reformulated four‐node shell element (RFNS) is employed in the numerical analyses. It is shown that the classical benchmark tests, in addition to testing the reliability and robustness of shell elements, also represent strong challenging tests for the asymptotic behaviour of shell elements. In the course of the numerical investigation of the asymptotic behaviour of the classical benchmark problems, the reliability and efficiency of the RFNS element already established by means of the classical configuration of the benchmark tests is re‐confirmed in all cases of the corresponding asymptotic test configurations. Copyright © 2002 John Wiley & Sons, Ltd.     

Modelling edge effects with the C0 plate bending elements: Part 1. Analysis of the mechanism

The behaviour of the C⁰ plate elements in modelling edge zone effects is analysed by utilizing the classical and a recently proposed formulation. Boundary layers are shown to develop under the activation of an edge zone moment redistribution mechanism, being part of a more generalized moment redistribution mechanism triggered by the in-plane twisting stiffness of the model.     

Evidence for Novel Action at the Cell‐Binding Site of Human Angiogenin Revealed by Heteronuclear NMR Spectroscopy,in silico and in vivo Studies

A member of the ribonuclease A superfamily, human angiogenin (hAng) is a potent angiogenic factor. Heteronuclear NMR spectroscopy combined with induced‐fit docking revealed a dual binding mode for the most antiangiogenic compound of a series of ribofuranosyl pyrimidine nucleosides that strongly inhibit hAng's angiogenic activity in vivo. While modeling suggests the potential for simultaneous binding of the inhibitors at the active and cell‐binding sites, NMR studies indicate greater affinity for the cell‐binding site than for the active site. Additionally, molecular dynamics simulations at 100 ns confirmed the stability of binding at the cell‐binding site with the predicted protein–ligand interactions, in excellent agreement with the NMR data. This is the first time that a nucleoside inhibitor is reported to completely inhibit the angiogenic activity of hAng in vivo by exerting dual inhibitory activity on hAng, blocking both the entrance of hAng into the cell and its ribonucleolytic activity.