Dependability Benchmarking & Prediction: A Grand Challenge Technology Problem
نویسندگان
چکیده
Ab stract We pro pose the grand chal lenge prob lem of de pend abil ity benchmarking and pre dic tion for real-time mis sion-crit i cal sys tems (RTMCSs). Eval u ating de pend abil ity would quan tify the de gree of re li ance that could jus ti fi ably be placed on a crit i cal sys tem, even in the face of par tial fail ures or ex cep tional con di tions. A com pre hen sive re sult would re quire an inter-dis ci plin ary ap proach em brac ing the en tire prod uct lifecycle. While there are sig nif i cant tech ni cal hur dles to both as sess ing the de pend abil ity of in di vid ual el e ments and com bin ing re sul tant mea sures, a vi a ble ap proach must be found to en sure that the com put ing sys tems our so ci ety is com ing to de pend upon will be re li able, avail able, safe, and se cure. The par tic i pa tion of sev eral com mu ni ties, in clud ing the Real Time Com puting com mu nity, is vi tal to suc cess fully ad dress this chal lenge.
منابع مشابه
An Overview of Existing Tools for Fault-Injection and Dependability Benchmarking in Grids
In this paper we review several existing tools for fault injection and dependability benchmarking in grids. We emphasis on the FAIL-FCI fault-injection software that has been developed in INRIA Grand Large, and a benchmark tool called QUAKE that has been developed in the University of Coimbra. We present the state-of-the-art and we explain the importance of these tools for dependability assessm...
متن کاملFault-Injection and Dependability Benchmarking for Grid Computing Middleware
In this paper we will present some work on dependability benchmarking for Grid Computing that represents a common view between two groups of Core-Grid: INRIA-Grand Large and University of Coimbra. We present a brief overview of the state of the art, followed by a presentation of the FAIL-FCI system from INRIA that provides a tool for fault-injection in large distributed systems. Then we present...
متن کاملTowards a Framework for Dependability Benchmarking
The goal of dependability benchmarking is to provide generic ways for characterizing the behavior of components and computer systems in the presence of faults, allowing for the quantification of dependability measures. Beyond existing evaluation techniques, dependability benchmarking must provide a reproducible and cost-effective way of performing this evaluation either as stand alone assessmen...
متن کاملAmbient Dependability
This paper tries, on one side, to raise awareness on the level of complexity of future computer-based interconnected systems/infrastructures, at least as they are envisioned, and, on the other side, on the level of dependability we are today able to justify with confidence. This paper does not provide solutions, but tries to motivate that fundamental methods and methodologies must be reconsider...
متن کاملA Framework for Dependability Benchmarking
This paper outlines a framework for defining dependability benchmarks of computer systems that is being investigated by the European project DBench*. The multiple dimensions of the problem are classified, then examples of benchmarking scenarios are presented. Finally, some research issues are discussed.
متن کامل