FailViz: A Tool for Visualizing Fault Injection Experiments in Distributed Systems

Cotroneo, Domenico; Simone, Luigi De; Liguori, Pietro; Natella, Roberto; Bidokhti, Nematollah

doi:10.1109/edcc.2019.00036

Cited by 8 publications

(7 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Similarly, spurious anomalies on REST API calls often denote exceptions raised by the system, and are more representative of the failure modes. To better understand this problem, Figure 3 shows a graphical representation of the activation of components in the Open-Stack cloud computing system during a fault-injection experiment [45]. The figure divides events into common, spurious, and omitted events, as described in the § 3.3.…”

Section: Open Issuesmentioning

confidence: 99%

Enhancing the Analysis of Software Failures in Cloud Computing Systems with Deep Learning

Cotroneo,

De Simone,

Liguori

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Identifying the failure modes of cloud computing systems is a difficult and time-consuming task, due to the growing complexity of such systems, and the large volume and noisiness of failure data. This paper presents a novel approach for analyzing failure data from cloud systems, in order to relieve human analysts from manually fine-tuning the data for feature engineering. The approach leverages Deep Embedded Clustering (DEC), a family of unsupervised clustering algorithms based on deep learning, which uses an autoencoder to optimize data dimensionality and inter-cluster variance. We applied the approach in the context of the OpenStack cloud computing platform, both on the raw failure data and in combination with an anomaly detection pre-processing algorithm. The results show that the performance of the proposed approach, in terms of purity of clusters, is comparable to, or in some cases even better than manually fine-tuned clustering, thus avoiding the need for deep domain knowledge and reducing the effort to perform the analysis. In all cases, the proposed approach provides better performance than unsupervised clustering when no feature engineering is applied to the data. Moreover, the distribution of failure modes from the proposed approach is closer to the actual frequency of the failure modes.

show abstract

Section: Open Issuesmentioning

confidence: 99%

Enhancing the Analysis of Software Failures in Cloud Computing Systems with Deep Learning

Cotroneo,

De Simone,

Liguori

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…They apply FaultCheck with QuickCheck on both the End to End library and the quadcopter simulator. At (2019), Fibich et al [17] [18] present the FailViz tool (fault injection visualize) implemented for OpenStack by the anomaly detection algorithm, in their approach distributed systems analysis as a black-box collection interacting during service interfaces.…”

Section: Literature Reviewmentioning

confidence: 99%

FIBR-OSS: fault injection model for bug reports in open-source software

Alazawi

Al-Salam²

2020

IJEECS

View full text Add to dashboard Cite

<span>For assessment of system dependability, fault injection techniques are used to expedite the presence of an error or failure in the system, which helps evaluate fault tolerance and system failure prediction. Defects classification and prediction is the principal significant advance in the trustworthiness evaluation of complex software systems such as open-source software since it can quickly be affected by the reliability of those systems, improves performance, and lessening the product cost. In this context, a new prototype of the fault injection model is presented, FIBR-OSS (Fault Injection for Bug Reports in Open-Source Software). FIBR-OSS can support developers to evaluate the system performance during phase's development for its dependability attributes such as reliability and system dependability means such as fault prediction or forecasting. FIBR-OSS is used for fault speed-up to test the system's failure prediction performance. Some machine learning techniques are implemented on bug reports produced existing by the bug tracking system as datasets for failure prediction techniques, some of those machine learning techniques are used in our approach.</span>

show abstract

“…These API calls are visualized as events on timelines as interactive plots. An example of visualization can be found in a previous study [59].…”

Section: Advanced Featuresmentioning

confidence: 99%

ProFIPy: Programmable Software Fault Injection as-a-Service

Cotroneo,

De Simone,

Liguori

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

In this paper, we present a new fault injection tool (ProFIPy) for Python software. The tool is designed to be programmable, in order to enable users to specify their software fault model, using a domain-specific language (DSL) for fault injection. Moreover, to achieve better usability, ProFIPy is provided as software-as-a-service and supports the user through the configuration of the faultload and workload, failure data analysis, and full automation of the experiments using containerbased virtualization and parallelization.

show abstract

FailViz: A Tool for Visualizing Fault Injection Experiments in Distributed Systems

Cited by 8 publications

References 19 publications

Enhancing the Analysis of Software Failures in Cloud Computing Systems with Deep Learning

Enhancing the Analysis of Software Failures in Cloud Computing Systems with Deep Learning

FIBR-OSS: fault injection model for bug reports in open-source software

ProFIPy: Programmable Software Fault Injection as-a-Service

Contact Info

Product

Resources

About