Hello World! Welcome to my personal website.
I'm currently a PhD Student in computer science at Sorbonne Université (previously UPMC). I am part of the Delys INRIA team at Laboratoire d'Informatique de Paris 6 (LIP6), under the supervision of Marc Shapiro.
My research interest is the design of highly available distributed systems, principally consistency protocols in case of replication between Datacenters and Edge devices.
My current thesis work is part of LightKone EU Project.
More detailsPre-implementation: System specification and design
Cloud-scale services improve availability and latency by geo-replicating data in several data centers (DC) across the world. Nevertheless, the closest DC is often still too far away for an optimal user experience. To remain available at all times, client-side applications need to cache data at client machines, caching data at client machines can improve availability and latency for many applications, and also allow for temporary disconnection. This approach is used in many recent cloud services, like Google Drive RT API or Mobius [3, 5, 9, 16], where developers implement caching and buffering at application level, but it doesn’t ensure system-wide consistency guarantees.
Keywords : Geo-replication, Partial Replication, Edge Computing, Causal Consistency, Peer-to-peer.
Publié à Compas 2017, Sophia Antipolis le 27 juin 2017
Pour augmenter les performances et la disponibilité, les bases de données sont généralement répliquées sur différents serveurs au sein de centres de données à travers le monde.
Cependant, la réplication implique quelques problèmes de cohérence.
La cohérence causale est un choix intéressant pour construire ce modèle de bases de données.
Elle permet aux clients d'observer un état cohérent par rapport à leurs écritures, en incluant les opérations qu'ils ont précédemment observé, tout en minimisant les anomalies pour le programmeur. Cependant, les mises en œuvre actuelles de la cohérence causale sont susceptibles de connaitre des ralentissements en chaîne à l'échelle de plusieurs centres de données. Ce papier décrit la conception d'un système causalement cohérent, évolutif, et non exposé à l'impact que peut avoir un serveur lent ou défaillant, sur la disponibilité des données.
Mots-clés : Bases de données distribuées, géo-replication, cohérence causale, disponibilité sous partition.
Running AngularJS paired up with RequireJS involves configuring few tweaks and hacks, especially if trying to preserve testability of Angular app. This seed project has been created to setup the entire front-end stack correctly and help developers get started with their projects.
Simple web-based app that allows you to team up, organize and prepare for online, competetive gameplay. Implemented only to an MVP stage in order to test it with a small group of gamers, it has turned out to be impractical. Build with AngularJS and Semantic UI.
Spellstack is a web-based toolset for Magic: The Gathering players. Using Spellstack users can put together a well-balanced, powerful deck for your next casual or tournament game. Additional tools such as random hand, statistics etc. help users evaluate deck's potential and performance.
Cloud-scale services improve availability and latency by geo-replicating data in several data center across the world. Nevertheless, the closest data center is often still too far away for an optimal user experience. To remain available at all times, client-side applications need to cache data at client machines. This approach is used in many recent cloud services, where developers implement caching and buffering at application level, but it doesn’t ensure system-wide consistency guarantees.
My research work is on the design of highly available distributed systems, principally consistency protocols in case of replication between Datacenters and Edge Computing devices.
My current work is part of EU project LightKone that aims to develop a scientifically sound and industrially validated model for doing general-purpose computation on edge networks. An edge network consists of a large set of heterogeneous, loosely coupled computing nodes situated at the logical extreme of a network. Common examples are community networks and Internet of Things networks, and networks including mobile devices, personal computers, and points of presence including Mobile Edge Computing. Internet applications are increasingly running on edge networks, to reduce latency, increase scalability, resilience, and security, and permit local decision making.
I teach the following courses:
- Security and System Administration (master 1).(2017, 2018, 2019)
- Multicore Kernels and Virtualisation (master 2), memory garbage collection part. (2018, 2019)
- Introduction to operating systems (licence 2). (2019)
- Introduction to Java langage (licence 2). (2018)
Fighting fragmentation due to virtualization in the Linux kernel: working-sets size estimating. Provide mechanisms, within the Linux kernel, to properly and efficiently size the cache available in a container, by offering different heuristics to improve page age approximation, at an acceptable cost.
Calculation and optimisation of software load distribution on an embedded automotive board. Linux Real-Time patches and Yocto recipes for SabreLite MX6 Board.
Automating forms processing of market studies, from a web based application.
Address :
Ilyas Toumlilt
Campus Pierre et Marie Curie
Sorbonne Université - LIP6
Case Courrier 169
Tower 26-00, Floor 2, Office 234
4 Place Jussieu
75252 PARIS CEDEX 05
FRANCE
Phone: +33 (0)1 44 27 88 17
Email: ilyas.toumlilt (at) lip6.fr
