Software aging and multifractality of memory resources

Abstract

We investigate the dynamics of monitored memory resource utilizations in an operating system under stress using quantitative methods of fractal analysis. In the experiments, we recorded the time series representing various memory related parameters of the operating system. We observed that parameters demonstrate clear multifractal behavior. The degree of fractality of these time series tends to increase as the system workload increases. We conjecture that the Hölder exponent that measures the local rate of fractality may be used as a quantitative measure of software aging. We propose a simple proactive computer crash avoidance strategy based on the online fractal analysis of system memory resource observations.

Software fault mitigation and availability assurance techniques

“…Using a non-parametric technique, Garg et al determined the global aging trend and calculate the estimated time until complete exhaustion via linear extrapolation for each resource. In case some form of rejuvenation or periodicity is already implemented by the system, as in the Apache Web server , piecewise linear (Castelli et al 2001), autoregressive time series with deterministic seasonal component , nonlinear statistical methods (Hoffman et al 2006), and fractal-based methods (Shereshevsky et al 2003) have also been used on such data. Regardless of the prediction method used, the resources selected for monitoring must be determined to minimize the monitoring overhead.…”

A Nonlinear Approach to Modeling of Software Aging in a Web Server

“…Based on the collected data, they construct software rejuvenation model to get the optimal rejuvenation schedule. Shereshevsky et al [21] monitor the Hölder exponent (a measure of the local rate of fractality, refer to [21]) of the system parameters and find that system crashes are often preceded by the second abrupt increase in this measure.…”

Non-parametric Predictive Inference of Preventive Rejuvenation Schedule in Operational Software Systems

“…For instance, operating system resources such as swap space and free memory available are progressively depleted due to defects in software such as memory leaks and incomplete cleanup of resources after use. It is well known that software aging will affect the performance of applications and eventually cause them to fail [1], [2], [7], [8], [15], [23], [29]. Software aging has been observed in widely-used communication software like Internet Explorer, Netscape and xrn as well as commercial * The present research was partially supported by Grant-in-Aids for Scientific Research from the Ministry of Education, Sports, Science and Culture of Japan under Grant Nos.…”