Prediction of the Inter-Node Communication Costs of a New Gyrokinetic Code with Toroidal Domain

We consider the communication costs of gyrokinetic plasma physics simulations running at large scale. For this we apply virtual decompositions of the toroidal domain in three dimensions and additional domain cloning to existing simulations done with the ORB5 code. The communication volume and the number of communication partners per timestep for every virtual task (node) are evaluated for the particles and the structured mesh. Thus the scaling properties of a code with the new domain decompositions are derived for simple models of a modern computer network and corresponding processing units. The effectiveness of the suggested decomposition has been shown. For a typical simulation with 2 . 10(9) particles and a mesh of 256 x 1024 x 512 grid points scaling to 2, 800 nodes should be achieved.

Load Sharing for Multiprocessor Network Nodes

This thesis discusses techniques for sharing the processing load among multiple processing units within systems that act as nodes in a data communications network. Load-sharing techniques have been explored in the field of computer science for many years and their beneits are well known, including better utilization of processing capacity and enhanced system fault tolerance. We discuss deploying such methods in the specifics of the networking environment. We concentrate particularly on the data plane, or the data packet-processing tasks. After reviewing the main results in the fields of load sharing and multiprocessor networking systems architectures, we conduct a preparatory optimization study of a router system to gain better understanding of the optimization issues in a particular multiprocessor system. The main contribution of this thesis, the adaptive load-sharing method, is presented next. We first formulate the optimization problem of mapping packets to processors. The goal is to minimize the likelihood of flow reordering, while respecting certain system constraints, such as the acceptable probability of a packet loss. As we show that the task is an NP-complete problem, we propose a heuristic method that uses an adaptive hash-based mapping to assign packets to processors. We demonstrate its advantages and prove that the method adaptation policy possesses the key minimal disruption property with respect to the mapping. In other words, the adaptation results in a minimum number of ows being moved among processing units. Further on, the method is validated in an extensive set of simulations designed to imitate the networking environment. Finally, two sample applications, an architecture of a multiprotocol router and an implementation of a server load balancer on a network processor demonstrate the applicability of the method.

2003

Artificial immune system for the Internet

Slavisa Sarafijanovic

We investigate the usability of the Artificial Immune Systems (AIS) approach for solving selected problems in computer networks. Artificial immune systems are created by using the concepts and algorithms inspired by the theory of how the Human Immune System (HIS) works. We consider two applications: detection of routing misbehavior in mobile ad hoc networks, and email spam filtering. In mobile ad hoc networks the multi-hop connectivity is provided by the collaboration of independent nodes. The nodes follow a common protocol in order to build their routing tables and forward the packets of other nodes. As there is no central control, some nodes may defect to follow the common protocol, which would have a negative impact on the overall connectivity in the network. We build an AIS for the detection of routing misbehavior by directly mapping the standard concepts and algorithms used for explaining how the HIS works. The implementation and evaluation in a simulator shows that the AIS mimics well most of the effects observed in the HIS, e.g. the faster secondary reaction to the already encountered misbehavior. However, its effectiveness and practical usability are very constrained, because some particularities of the problem cannot be accounted for by the approach, and because of the computational constrains (reported also in AIS literature) of the used negative selection algorithm. For the spam filtering problem, we apply the AIS concepts and algorithms much more selectively and in a less standard way, and we obtain much better results. We build the AIS for antispam on top of a standard technique for digest-based collaborative email spam filtering. We notice un advantageous and underemphasized technological difference between AISs and the HIS, and we exploit this difference to incorporate the negative selection in an innovative and computationally efficient way. We also improve the representation of the email digests used by the standard collaborative spam filtering scheme. We show that this new representation and the negative selection, when used together, improve significantly the filtering performance of the standard scheme on top of which we build our AIS. Our complete AIS for antispam integrates various innate and adaptive AIS mechanisms, including the mentioned specific use of the negative selection and the use of innate signalling mechanisms (PAMP and danger signals). In this way the AIS takes into account users' profiles, implicit or explicit feedback from the users, and the bulkiness of spam. We show by simulations that the overall AIS is very good both in detecting spam and in avoiding misdetection of good emails. Interestingly, both the innate and adaptive mechanisms prove to be crucial for achieving the good overall performance. We develop and test (within a simulator) our AIS for collaborative spam filtering in the case of email communications. The solution however seems to be well applicable to other types of Internet communications: Internet telephony, chat/sms, forum, news, blog, or web. In all these cases, the aim is to allow the wanted communications (content) and prevent those unwanted from reaching the end users and occupying their time and communication resources. The filtering problems, faced or likely to be faced in the near future by these applications, have or are likely to have the settings similar to those that we have in the email case: need for openness to unknown senders (creators of content, initiators of the communication), bulkiness in receiving spam (many recipients are usually affected by the same spam content), tolerance of the system to a small damage (to small amounts of unfiltered spam), possibility to implicitly or explicitly and in a cheap way obtain a feedback from the recipients about the damage (about spam that they receive), need for strong tolerance to wanted (non-spam) content. Our experiments with the email spam filtering show that our AIS, i.e. the way how we build it, is well fitted to such problem settings.

EPFL2008

Artificial immune system for the Internet

Slavisa Sarafijanovic

EPFL2008