Statement Nicolas Schiper

نویسنده

  • Nicolas Schiper
چکیده

Cloud-based applications are everywhere around us. They range from performance sensitive services such as web search, e-commerce, and social networking to mission-critical applications such as air-traffic control and the power grid. These applications tend to be complex, involve a large number of computers, and must face all sorts of failures ranging from power outages and software bugs to malicious attackers. My research interests are centered around making these applications reliable, trustworthy, and scalable. Designing protocols that meet all these requirements is not only a science but also an art and it is a very exciting topic. As such, I design, build, and evaluate protocols to make these services fault-tolerant and scalable, and I use formal methods to provide bug-free code for critical components. As fault-tolerant storage systems have become pervasive in today’s data centers, I have also started investigating the issue of energy-efficient cloud storage. In this line of research, I strive to maximize the performance obtained per Watt by adapting the replication protocol to the workload. My approach to research consists in identifying a problem, precisely stating what properties the solution should guarantee, and exploring the space of solutions. I carry out this exploration both at a theoretical level to distinguish what can be done from what cannot, and at a practical level by building the complete system for it to be extensively evaluated. As a theoretical model cannot fully encompass the complexity of a real system, the initial formal model and algorithms may have to be adapted. This can take the form of refining the fault-model, e.g., in a single tenant cloud hardware and software failures may be more common than malicious attacks; or it may mean trading off some performance for the sake of simplicity. Empirical evaluations often reveal protocol behaviors not foreseen in the design process and are thus essential. To date, I have successfully applied this approach to several projects, various of which I will describe below.

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Optimistic Algorithms for Partial Database Replication

In this paper, we study the problem of partial database replication. Numerous previous works have investigated database replication, however, most of them focus on full replication. We are here interested in genuine partial replication protocols, which require replicas to permanently store only information about data items they replicate. We define two properties to characterize partial replica...

متن کامل

Ring Paxos: High-Throughput Atomic Broadcast†

Atomic broadcast is an important communication primitive often used to implement state-machine replication. Despite the large number of atomic broadcast algorithms proposed in the literature, few papers have discussed how to turn these algorithms into efficient executable protocols. This paper focuses on a class of atomic broadcast algorithms based on Paxos, with its corresponding desirable pro...

متن کامل

ShadowDB: A Replicated Database on a Synthesized Consensus Core

This paper describes ShadowDB, a replicated version of the BerkeleyDB database. ShadowDB is a primarybackup based replication protocol where failure handling, the critical part of the protocol, is taken care of by a synthesized consensus service that is correct by construction. The service has been proven correct semiautomatically by the Nuprl proof assistant. We describe the design and process...

متن کامل

Cooperative client caching strategies for social and web applications

We evaluate the efficiency and cost of different placement strategies for a distributed cache implemented on the clients of an online social network or web service. In our system model, the service maintains a directory for content that tracks the location of objects. The service informs requesting clients of these locations and the clients will cache, serve, and push content according to direc...

متن کامل

Brief Announcement: Optimistic Algorithms for Partial Database Replication

Database replication protocols based on group communication have recently received a lot of attention. The main reason for this stems from the fact that group communication primitives offer adequate properties, namely agreement on the messages delivered and on their order, to implement synchronous database replication. Most of the complexity involved in synchronizing database replicas is handle...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2013