Reliability analysis in distributed systems

Raghavendra, C.S.; Kumar, V. Ravi; Hariri, Salim

doi:10.1109/12.2173

Cited by 56 publications

(9 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [6], Distributed Program Reliability (DPR) and Distributed System Reliability (DSR) are two metrics firstly introduced to the reliability evaluation of distributed systems by Raghavendra. Also, Raghavendra propose an algorithm based on graph-traversal to calculate DSR and DPR.…”

Section: Related Workmentioning

confidence: 99%

Workload-aware Reliability Evaluation Model in Grid Computing

Hu¹

2012

JCP

View full text Add to dashboard Cite

To address the issue of reliability evaluation in dynamic grid environment, a workload-aware reliability evaluation model is proposed, in which queuing system is applied to describe the dynamic workload and working of grid resources. Meanwhile, a new type of resource fault, namely Deadline-Miss fault, is introduced to evaluate the reliability of real-time jobs. The validity of the proposed model and its approach to calculate real-time job’s reliability are presented theoretically. Extensive experiments are conducted to verify its performance, and the results show that the proposed model can significantly improve the accuracy of reliability evaluation in presence of dynamic workload. Also, scheduling algorithm based on this model can reduce the jobs’ mean response time and the deadline-miss rate

show abstract

Section: Related Workmentioning

confidence: 99%

Workload-aware Reliability Evaluation Model in Grid Computing

Hu¹

2012

JCP

View full text Add to dashboard Cite

show abstract

“…In contrast, our framework covers several types of compromises. Some early works on distributed systems focus on the probability of successful execution, which is to a certain extent similar to the probabilities of compromises (i.e., C , A IN and A EX ). But those works do not integrate two aspects of performance into a comparative metric.…”

Section: Related Workmentioning

confidence: 99%

Evaluating Intrusion‐Tolerant Certification Authority Systems

Lin

Jing

Liu

2011

Quality & Reliability Eng

View full text Add to dashboard Cite

Various intrusion-tolerant certification authority (CA) systems have been proposed to provide attack resilient certificate signing (or update) services. However, it is difficult to compare them against each other directly, due to the diversity in system organizations, threshold signature schemes, protocols and usage scenarios. We present a framework for intrusion-tolerant CA system evaluation, which consists of three components, namely, an intrusion-tolerant CA model, a threat model and a metric for comparative evaluation. The evaluation framework covers system organizations, protocols, usage scenarios, the period of certificate validity, the revocation rate and the mean time to recovery. Based on the framework, four representative systems are evaluated and compared in three typical usage scenarios, producing reasonable and insightful results. The interdependence between usage scenarios and system characteristics is investigated, providing a guideline to design better systems for different usage scenarios. The proposed framework provides an effective and practicable method to evaluate intrusion-tolerant CA systems quantitatively, and helps customers to choose and configure an intrusion-tolerant CA system. Moreover, the comparison results offer valuable insights to further improve the attack resilience of intrusion-tolerant CA systems.To validate the framework, an in-depth comparative evaluation of four representative intrusion-tolerant CA systems (ITTC, 53 ARECA, 25 COCA 57 and MOCA 56 ), is conducted. After analyzing these systems, we evaluate them in three typical usage scenarios (LANs, the Internet and ad hoc networks), and study the evaluation results with small variations of the usage scenario parameters. The interdependence between usage scenarios and system characteristics is also studied based on the evaluation results. Then, several conclusions and suggestions for designing better systems are presented. The analysis can be applied to facilitate designing a new system to obtain optimal performance in a certain usage scenario. Note that in this paper, performance means attack resilience.Although COCA provides two types of certificate services, that is, update and query, only the certificate update service is compared with other CA systems in our evaluation framework because a commodity CA typically does not support certificate query. To support attack resilient certificate query, the COCA design is not solely driven by maximizing the resilience of certificate update services. As a result, the comparisons are not meant to judge the overall design of COCA. Instead, the framework compares only the certificate update service of COCA with other genuine certificate update solutions. To make this point clear, in the rest of this paper we denote COCA as COCA CUS (certificate update service). of the Internet P C , P A and P D are estimated based on statistics on the Internet. In 2003, 202,369,889 hosts (denoted as N h ) were advertised in Internet domain survey (DNS) averagely, 22 and 137,529 incidents (denoted as ...

show abstract

“…A number of algorithms have been proposed to estimate the reliability of distributed systems and distributed applications. Raghavendra et al (1988) introduced two reliability measures: distributed program reliability and distributed system reliability. An efficient approach based on graph traversal is developed to evaluate the proposed measures.…”

Section: Related Workmentioning

confidence: 99%