Measurement of failure rate in widely distributed software

Chillarege, Ram; Biyani, S.; Rosenthal, Jeffrey S.

doi:10.1109/ftcs.1995.466957

Cited by 61 publications

(37 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Gray [8] presented results from a census of Tandem systems. Chillarege [7] presented a study of the impact of failures on customers and the fault lifetimes. Sullivan [23], [24] examined software defects occurring in operating systems and databases (based on field data).…”

Section: Error and Failure Analysis Of A Lan Of Windows Nt-based Serversmentioning

confidence: 99%

Measurement-Based Analysis of System Dependability Using Fault Injection and Field Failure Data

Iyer

Kalbarczyk

2002

Performance Evaluation of Complex Systems: Techniques and Tools

View full text Add to dashboard Cite

Abstract. The discussion in this paper focuses on the issues involved in analyzing the availability of networked systems using fault injection and the failure data collected by the logging mechanisms built into the system. In particular we address: (1) analysis in the prototype phase using physical fault injection to an actual system. We use example of fault injection-based evaluation of a software-implemented fault tolerance (SIFT) environment (built around a set of self-checking processes called ARMORS) that provides error detection and recovery services to spaceborne scientific applications and (2) measurement-based analysis of systems in the field. We use example of LAN of Windows NT based computers to present methods for collecting and analyzing failure data to characterize network system dependability. Both, fault injection and failure data analysis enable us to study naturally occurring errors and to provide feedback to system designers on potential availability bottlenecks. For example, the study of failures in a network of Windows NT machines reveals that most of the problems that lead to reboots are software related and that though the average availability evaluates to over 99%, a typical machine, on average, provides acceptable service only about 92% of the time.

show abstract

Section: Error and Failure Analysis Of A Lan Of Windows Nt-based Serversmentioning

confidence: 99%

Measurement-Based Analysis of System Dependability Using Fault Injection and Field Failure Data

Iyer

Kalbarczyk

2002

Performance Evaluation of Complex Systems: Techniques and Tools

View full text Add to dashboard Cite

show abstract

“…F C M i`F C M j = 1 ;P ij ; n X k=1 P ik P kj ; n X l=1 n X k=1 P ik P kl P lj ;: : : (3) (At some point, higher-order terms are likely to be small enough to be neglected.) The separation value gives an accurate estimate of the interaction between FCMs, as all FCMs at the same level get considered.…”

Section: Measuring Separationmentioning

confidence: 99%

A framework for dependability driven software integration

Suri

Ghosh²,

Marlowe³

Proceedings. 18th International Conference on Distributed Computing Systems (Cat. No.98CB36183)

View full text Add to dashboard Cite

The integration of system and SW functions for efciency, performance and especially dependability is of interest from a research and system design perspective. In this paper, we propo s e a f r amework for directing the process of integration of SW functions, with the objective of designing and maintaining desired dependability attributes of the system over the integration process. Rules of composition for integrated functions, and measures to quantify the goodness of dependable system integration are also addressed.

show abstract

“…We chose to consider operating system resource exhaustion, in particular, memory exhaustion, in addition to the hardware faults because previous studies have shown that memory exhaustion may be a dominant factor in the "aging" of operating systems [12,36]. Likewise, we chose the specific application-level faults because a previous study suggests that they are the dominant categories of application errors [11]. We could have assumed a completely generic application fault model, such as the crashing of a process.…”

Section: Fault Injection and Fault Modelmentioning

confidence: 99%

“…Recall that to make the modeling tractable, we assume that faults in different components are not correlated and all fault arrivals are exponentially distributed. We have done our best to derive meaningful parameters from the available data [11,12,15,21,35,34,36]. However, data is sparse, particularly for application-level errors.…”

Section: Performability Of the Press Versionsmentioning

confidence: 99%

“…Thus, we examine performability for a range, once per day to once per month, of MTTFs for application level faults. In addition, because we have multiple classes of errors, we divided the application fault rate between these errors according to the distribution observed in [11]. This led to approximately the following ratio: process crash 40%, process hang 40%, null pointer 8%, off by N data pointer 9%, off by N size 2%.…”

Section: Performability Of the Press Versionsmentioning

confidence: 99%

See 1 more Smart Citation