Couche application | EPFL Graph Search

La couche application est la du modèle OSI. Définition OSI (ISO 7498-1) La couche application est surtout, du point de vue du modèle, le point d'accès aux services réseaux. Comme le modèle n'a pas pour rôle de spécifier les applications, il ne spécifie pas de service à ce niveau. La couche d'application représente des données pour l'utilisateur ainsi que du codage et un contrôle du dialogue : des mécanismes de communication offerts aux applications de l'utilisateur. Exemples de protocoles Puisqu'il n'y a pas beaucoup de méthodes fondamentalement différentes permettant d'assurer les fonctions des couches 2 à 6, leur éventail de protocoles est donc assez restreint. En revanche, au niveau application la diversité est la règle. En se limitant au monde IP, on trouve par exemple et sans être exhaustif :

4 protocoles orientés transfert de fichiers : (IETF), (Sun Microsystems) et , SMB/ (Microsoft) ;
5 protocoles orientés messageries : Simple Mail Transfe

R3P2: a Replicated Request-Response Pair Protocol

Antoine Albertelli

Consensus protocol have seen increased usage in recent years due to the industry shift to distributed computing. However, it has traditionally been implemented in the application layer. We propose to move the consensus protocol in the transport layer, to offer reliable ordered delivery of messages to applications. Our implementation builds on R2P2, a novel RPC framework for datacenter applications. It can run both using Linux UDP sockets or kernel bypass using DPDK. We observe tail latency increase of only 10 μs and a throughput loss of only 13% compared to the unreplicated application, showing that easy-to-use consensus can also have high performance.

2019

Contact.engineering-Create, analyze and publish digital surface twins from topography measurements across many scales

Abhijeet Gujrati, Till Junge

The optimization of surface finish to improve performance, such as adhesion, friction, wear, fatigue life, or interfacial transport, occurs largely through trial and error, despite significant advancements in the relevant science. There are three central challenges that account for this disconnect: (1) the challenge of integration of many different types of measurement for the same surface to capture the multi-scale nature of roughness; (2) the technical complexity of implementing spectral analysis methods, and of applying mechanical or numerical models to describe surface performance; (3) a lack of consistency between researchers and industries in how surfaces are measured, quantified, and communicated. Here we present a freely-available internet-based application (available at https://contact.engineering) which attempts to overcome all three challenges. First, the application enables the user to upload many different topography measurements taken from a single surface, including using different techniques, and then integrates all of them together to create a digital surface twin. Second, the application calculates many of the commonly used topography metrics, such as rootmean-square parameters, power spectral density (PSD), and autocorrelation function (ACF), as well as implementing analytical and numerical calculations, such as boundary element modeling (BEM) for elastic and plastic deformation. Third, the application serves as a repository for users to securely store surfaces, and if they choose, to share these with collaborators or even publish them (with a digital object identifier) for all to access. The primary goal of this application is to enable researchers and manufacturers to quickly and easily apply cutting-edge tools for the characterization and properties-modeling of real-world surfaces. An additional goal is to advance the use of open-science principles in surface engineering by providing a FAIR database where researchers can choose to publish surface measurements for all to use.

IOP Publishing Ltd2022

Non-Pareto Optimality of MPTCP: Performance Issues and a Possible Solution

Nicolas Gabriel Gast, Ramin Khalili, Jean-Yves Le Boudec, Miroslav Popovic, Utkarsh Upadhyay

MPTCP has been proposed as a mechanism to support transparently multiple connections to the application layer and is under discussion at the IETF. It can use effectively the available bandwidth and it improves throughput and fairness, compared to independent TCP flows in many scenarios. However we show, by measurements over our testbed and analytically, that MPTCP still suffers from two problems: (P1) upgrading some TCP users to MPTCP can reduce the throughput of others without any benefit to the upgraded users, which is a symptom of non-Pareto optimality; (P2) MPTCP users could be excessively aggressive towards TCPusers. We attribute these problems to the “Linked Increases”Algorithm(LIA) of MPTCP, and more specifically, to an excessive amount of traffic transmitted over congested paths. The design of LIA forces a tradeoff between optimal resource pooling and responsiveness. Hence, to provide good responsiveness MPTCP’s current implementation must depart from Pareto-optimality. We revisit the problem and show that it is possible to simultaneously provide these two properties. We implement the resulting algorithm, called Opportunistic “Linked Increases” Algorithm (OLIA), in the Linux kernel and study its performance over our testbed by simulations and by theoretical analysis. We prove that OLIA is Pareto-optimal, hence avoids the problems (P1) and (P2). Our mea- surements and simulations indicate that MPTCP with OLIA is as responsive and non-flappy as MPTCP with LIA, while solving problems (P1) and (P2).

2012

Contact.engineering-Create, analyze and publish digital surface twins from topography measurements across many scales

Abhijeet Gujrati, Till Junge

IOP Publishing Ltd2022