Software Rejuvenation Based Fault Tolerance Scheme for Cloud Applications

Abstract

Cloud applications are typically composed of multiple cloud service components communicating with each other through web service interfaces, where each component fulfills specified functionalities. Lack of effective fault tolerance scheme is one of major obstacles for enhancing availability and efficiency of complex and aging cloud application systems. In this paper, we propose a holistic software rejuvenation based fault tolerance scheme for cloud applications, which contains three indispensible parts: adaptive failure detection, aging degree evaluation, and checkpoint with trace replay based component rejuvenation. Through a preliminary and qualitative evaluation, it shows that our new fault tolerance scheme brings promising improvement on the availability of cloud applications.

Fault tolerant software systems using software configurations for cloud computing

“…An approach based on backup of virtual machines in the cloud [28] was proposed by Xinyi et al to improve system reliability. For more information on software rejuvenation interested reader may refer to [29][30][31][32]. c) Preemptive Migration: Migration of processes, operating systems and virtual machines enable load balancing, efficient resource usage, fault management and system maintenance.…”

Modern software cybernetics: New trends

“…Lack of effective fault tolerance scheme is one of the major obstacles for enhancing availability and efficiency of complex and ageing cloud application systems. Liu et al (2015) proposed an adaptive failure detection and ageing degree evaluation approach to predict which cloud service components deserved foremost to be rejuvenated and a component rejuvenation approach based on checkpoints with trace replay was proposed to guarantee the continuous running of cloud application systems.…”

“…The result proved that this software cybernetics method made software system easier to maintain. Liu et al (2015) proposed a holistic software rejuvenation based fault tolerance scheme for cloud applications, which contained three indispensable parts: adaptive failure detection, ageing degree evaluation, and checkpoint with trace replay based component rejuvenation. Through a preliminary and qualitative evaluation, it showed that the new fault tolerance scheme brought promising improvement on the availability of cloud applications.…”

Optimum Software Aging Prediction and Rejuvenation Model for Virtualized Environment

“…Jing Liu, et al, proposed an adaptive failure detection method depending on the CPU and memory usage of certain VMs. The transmission delay of monitoring packets between service components and the AFD (Aging failure Detector) unit are chosen as the basic runtime metrics for aging detection [6]. Yongquan Yan proves that choosing a proper data set is more important than choosing a method for software resource consumption forecasting [7].…”

“…A-GARC algorithm executes crossover function to select the best host for accommodating aged VMs. The algorithm used for genetic algorithm (GA) based task placement or relocation is given as follows: Step- 1 Create VM and install applications on certain host node Step-2 Forecast software ageing probability based on aging indicator metrics Step- 3 Perform Initial mapping of VMs and connected hosts and then use it as initial population for GA Step- 4 Identify the aged hosts using Step-2 so as to avoid any probable SLA violation and conflict during rejuvenation Step- 5 Identify the list of VMs allied with each host node, which are not under migration, so that SLA performance violation could be avoided Step- 6 Perform aged VMs selection and retrieve the list of all VMs ready for migration Step- 7 Sort all VMs on the basis of its aging status Step- 8 Retrieve the complete active hosts possessing minimal workload and resource under-consumption Step-9…”