A Self-tuning Failure Detection Scheme for Cloud Computing Service

Unreliable failure detectors are a basic building block of reliable distributed systems. Failure detectors are used to monitor processes of any application and provide process state information. This work presents an Internet Failure Detector Service (IFDS) for processes running in the Internet on multiple autonomous systems. The failure detection service is adaptive, and can be easily integrated into applications that require configurable QoS guarantees. The service is based on monitors which are capable of providing global process state information through a SNMP MIB. Monitors at different networks communicate across the Internet using Web Services. The system was implemented and evaluated for monitored processes running both on single LAN and on PlanetLab. Experimental results are presented, showing the performance of the detector, in particular the advantages of using the self-tuning strategies to address the requirements of multiple concurrent applications running on a dynamic environment.

show abstract

“…In [20] a failure detector that is capable of self-configuration is applied to a cloud computing environment.…”

Section: Failure Detectors and Related Workmentioning

confidence: 99%

A QoS-configurable failure detection service for internet applications

Turchetti

Duarte

Arantes³

et al. 2016

J Internet Serv Appl

View full text Add to dashboard Cite

show abstract

“…Based on the failure detection methods shown in [7,8], we propose an adaptive failure detection method. The CPU and memory usage of certain VMs, and the transmission delay of monitoring packets between service components and the AFD unit are chosen as the basic runtime metrics for indicating more comprehensively whether aging problems tend to cause service failures.…”

Section: Failure Detection and Evaluationmentioning

confidence: 99%

“…To improve computing accuracy, the computation of EAT utilizes actual arrival time of recent packets as the historical information in a sliding window, i.e., recent n packet p 1 , p 2 , ..., p n , and T 1 , T 2 , ..., T n are their actual arrival time according to AFD's local clock. EAT k+1 (k>n) is the theoretically expected arrival time of next packet, and it is estimated as follows based on studies in [7].…”

Section: ) Computing Expected Arrival Time (Eat)mentioning

confidence: 99%

Software Rejuvenation Based Fault Tolerance Scheme for Cloud Applications

Liu

Zhou

Buyya

2015

2015 IEEE 8th International Conference on Cloud Computing

View full text Add to dashboard Cite

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.

show abstract

“…Several works study detection of failure modes [33], [34]. The approach of the Gamose system [35] for monitoring the health of Grid applications can extend the CACS checks for application health without requiring application hooks.…”

Section: Fault Tolerance and Efficiency In The Cloudmentioning

confidence: 99%

Checkpointing as a Service in Heterogeneous Cloud Environments

Cao

Simonin

Cooperman³

et al. 2015

2015 15th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing

View full text Add to dashboard Cite

A non-invasive, cloud-agnostic approach is demonstrated for extending existing cloud platforms to include checkpoint-restart capability. Most cloud platforms currently rely on each application to provide its own fault tolerance. A uniform mechanism within the cloud itself serves two purposes: (a) direct support for long-running jobs, which would otherwise require a custom fault-tolerant mechanism for each application; and (b) the administrative capability to manage an over-subscribed cloud by temporarily swapping out jobs when higher priority jobs arrive. An advantage of this uniform approach is that it also supports parallel and distributed computations, over both TCP and InfiniBand, thus allowing traditional HPC applications to take advantage of an existing cloud infrastructure. Additionally, an integrated health-monitoring mechanism detects when longrunning jobs either fail or incur exceptionally low performance, perhaps due to resource starvation, and proactively suspends the job. The cloud-agnostic feature is demonstrated by applying the implementation to two very different cloud platforms: Snooze and OpenStack. The use of a cloud-agnostic architecture also enables, for the first time, migration of applications from one cloud platform to another.

show abstract

A Self-tuning Failure Detection Scheme for Cloud Computing Service

Cited by 68 publications

References 33 publications

A QoS-configurable failure detection service for internet applications

A QoS-configurable failure detection service for internet applications

Software Rejuvenation Based Fault Tolerance Scheme for Cloud Applications

Checkpointing as a Service in Heterogeneous Cloud Environments

Contact Info

Product

Resources

About