Unsupervised Detection of Microservice Trace Anomalies through Service-Level Deep Bayesian Networks

Liu, Ping; Xu, Haowen; Ouyang, Qianyu; Jiao, Rui; Chen, Zhekang; Zhang, Shenglin; Yang, Jiahai; Mo, Linlin; Zeng, Jice; Xue, Wenman; Pei, Dan

doi:10.1109/issre5003.2020.00014

Cited by 83 publications

(29 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…After detecting that there is a fault, an equally important task is to use the data-driven methods to narrow down the set of possible faults that may arise. This task is known as fault localization [5,6,14,25,28]. The localization can be done on various data types.…”

Section: Fault Localizationmentioning

confidence: 99%

Artificial Intelligence for IT Operations (AIOPS) Workshop White Paper

Bogatinovski,

Nedelkoski,

Acker

et al. 2021

Preprint

View full text Add to dashboard Cite

Section: Fault Localizationmentioning

confidence: 99%

Artificial Intelligence for IT Operations (AIOPS) Workshop White Paper

Bogatinovski,

Nedelkoski,

Acker

et al. 2021

Preprint

View full text Add to dashboard Cite

“…TraceAnomaly [45] and Nedelkoski et al [61] collect traces in training runs of a multi-service application and use them to train unsupervised neural networks. They then enact online anomaly detection by exploiting the trained neural networks to process the traces generated by the application while it is running in production.…”

Section: Unsupervised Learningmentioning

confidence: 99%

“…They then enact online anomaly detection by exploiting the trained neural networks to process the traces generated by the application while it is running in production. In particular, TraceAnomaly [45] trains a deep Bayesian neural network with posterior flow [59,71], which enables associating monitored traces with a likelihood to be normal, viz., not affected by performance anomalies. It also stores all seen service call paths, viz., all sequences of service interactions observed in the available traces.…”

Section: Unsupervised Learningmentioning

confidence: 99%

“…It also stores all seen service call paths, viz., all sequences of service interactions observed in the available traces. TraceAnomaly [45] then enacts online anomaly detection in two steps. It first checks whether a newly produced trace contains previously unseen call paths.…”

Section: Unsupervised Learningmentioning

confidence: 99%

“…It first checks whether a newly produced trace contains previously unseen call paths. If this is the case, TraceAnomaly [45] decides whether to consider the unseen call paths as functional anomalies for the application, based on whether they appear in a whitelist manually filled by the application operator to exclude false alarms (e.g., unseen call paths corresponding to new interactions occurring after service upgrades). If there is no functional anomaly, the trace is passed to the deep Bayesian neural network, which associates the monitored trace with its likelihood to be normal.…”

Section: Unsupervised Learningmentioning

confidence: 99%

See 2 more Smart Citations

Anomaly Detection and Failure Root Cause Analysis in (Micro)Service-Based Cloud Applications: A Survey

Soldani¹,

Brogi²

2021

Preprint

View full text Add to dashboard Cite

The momentum gained by microservices and cloud-native software architecture pushed nowadays enterprise IT towards multi-service applications. The proliferation of services and service interactions within applications, often consisting of hundreds of interacting services, makes it harder to detect failures and to identify their possible root causes, which is on the other hand crucial to promptly recover and fix applications. Various techniques have been proposed to promptly detect failures based on their symptoms, viz., observing anomalous behaviour in one or more application services, as well as to analyse logs or monitored performance of such services to determine the possible root causes for observed anomalies. The objective of this survey is to provide a structured overview and a qualitative analysis of currently available techniques for anomaly detection and root cause analysis in modern multi-service applications. Some open challenges and research directions stemming out from the analysis are also discussed.

show abstract

TraceRank: Abnormal service localization with dis‐aggregated end‐to‐end tracing data in cloud native systems

Huang

Chen

2021

J Software Evolu Process

View full text Add to dashboard Cite

Modern cloud native applications are generally built with a microservice architecture. To tackle various performance problems among a large number of services and machines, an end‐to‐end tracing tool is always equipped in these systems to track the execution path of every single request. However, it is nontrivial to conduct root cause analysis of anomalies with such a large volume of tracing data. This paper proposes a novel system named TraceRank to identify and locate abnormal services causing performance problems with dis‐aggregated end‐to‐end traces. TraceRank mainly includes an anomaly detection module and a root cause analysis module. The root cause analysis procedure is triggered when an anomaly is detected. To fully leverage the information provided by the tracing data, both the spectrum analysis and the PageRank‐based random walk methods are introduced to pinpoint abnormal services. The experiments in TrainTicket and Bookinfo microservice benchmarks and a real‐world system show that TraceRank can locate root causes with 90% in Precision and 86% in Recall. TraceRank has up to 10% improvement compared with several state‐of‐the‐art approaches in both Precision and Recall. Finally, TraceRank has good scalability and a low overhead to adapt to large‐scale microservice systems.

show abstract

Unsupervised Detection of Microservice Trace Anomalies through Service-Level Deep Bayesian Networks

Cited by 83 publications

References 29 publications

Artificial Intelligence for IT Operations (AIOPS) Workshop White Paper

Artificial Intelligence for IT Operations (AIOPS) Workshop White Paper

Anomaly Detection and Failure Root Cause Analysis in (Micro)Service-Based Cloud Applications: A Survey

TraceRank: Abnormal service localization with dis‐aggregated end‐to‐end tracing data in cloud native systems

Contact Info

Product

Resources

About