PREPARE: Predictive Performance Anomaly Prevention for Virtualized Cloud Systems

Tan, Yongmin; Nguyen, Hiep; Shen, Zhiming; Gu, Xiaohui; Venkatramani, Chitra; Rajan, Deepta

doi:10.1109/icdcs.2012.65

Cited by 131 publications

(96 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Medium to large scale cloud infrastructures run up to thousands of applications on limited computing resources. It is a daunting to keep track of the execution status of such huge applications base [ [34]; [62]]. Considering that these applications are composed of multiple service components and the complex topology of the infrastructure, the potential metric space is huge.…”

Section: Padbi Systems In the Cloud: Specific Requirementsmentioning

confidence: 99%

“…Moreover, services in IaaS clouds come in black-boxes with limited visibility by the cloud infrastructure provider. This limits the extent to which performance degradation issues can be diagnosed and resolved [[62]; [34]]. …”

Section: Padbi Systems In the Cloud: Specific Requirementsmentioning

confidence: 99%

“…Dynamic Resource Management. Due to the continuous flow of load in and out of the cloud, resource management tasks such as dynamic reconfiguration, consolidation and migration constantly change the operational context in which applications runs [ [34]; [122]]. This leads to higher frequency of anomalies.…”

Section: Padbi Systems In the Cloud: Specific Requirementsmentioning

confidence: 99%

“…Autonomic resource managers dynamically provision resources based on adaptive system policies to meet expected quality of service (QoS) and achieve optimal resource utilization levels [ [137]; [138]]. Delayed detection and manual resolutions does not fit the cloud model as they can cause prolonged performance violations with huge financial penalty and failure [[62]; [34]]. Therefore PADBI systems for the cloud are must be dynamic and proactive in nature [ [39]; [122]].…”

Section: Padbi Systems In the Cloud: Specific Requirementsmentioning

confidence: 99%

See 3 more Smart Citations

Performance Anomaly Detection and Bottleneck Identification

2015

View full text Add to dashboard Cite

In order to meet stringent performance requirements, system administrators must e↵ectively detect undesirable performance behaviours, identify potential root causes and take adequate corrective measures. The problem of uncovering and understanding performance anomalies and their causes (bottlenecks) in di↵erent system and application domains is well studied. In order to assess progress, research trends and identify open challenges, we have reviewed major contributions in the area and present our findings in this survey. Our approach provides an overview of anomaly detection and bottleneck identification research as it relates to the performance of computing systems. By identifying fundamental elements of the problem, we are able to categorize existing solutions based on multiple factors such as the detection goals, nature of applications and systems, system observability, and detection methods.

show abstract

Section: Padbi Systems In the Cloud: Specific Requirementsmentioning

confidence: 99%

Section: Padbi Systems In the Cloud: Specific Requirementsmentioning

confidence: 99%

Section: Padbi Systems In the Cloud: Specific Requirementsmentioning

confidence: 99%

Section: Padbi Systems In the Cloud: Specific Requirementsmentioning

confidence: 99%

See 2 more Smart Citations

Performance Anomaly Detection and Bottleneck Identification

2015

View full text Add to dashboard Cite

show abstract

“…Clouds present an automated and dynamic model, which conflicts with the manual/semiautomatic process of problem determination. An application running inside a cloud often appears opaque to the cloud provider, which makes it non-trivial to access fine-grained system and application measurements for problem detection [9].…”

Section: Introductionmentioning

confidence: 99%

CloudPD: Problem determination and diagnosis in shared dynamic clouds

Sharma

Jayachandran

Verma

et al. 2013

2013 43rd Annual IEEE/IFIP International Conference on Dependable Systems and Networks (DSN)

View full text Add to dashboard Cite

Abstract-In this work, we address problem determination in virtualized clouds. We show that high dynamism, resource sharing, frequent reconfiguration, high propensity to faults and automated management introduce significant new challenges towards fault diagnosis in clouds. Towards this, we propose CloudPD, a fault management framework for clouds. CloudPD leverages (i) a canonical representation of the operating environment to quantify the impact of sharing; (ii) an online learning process to tackle dynamism; (iii) a correlation-based performance models for higher detection accuracy; and (iv) an integrated end-to-end feedback loop to synergize with a cloud management ecosystem. Using a prototype implementation with cloud representative batch and transactional workloads like Hadoop, Olio and RUBiS, it is shown that CloudPD detects and diagnoses faults with low false positives (< 16%) and high accuracy of 88%, 83% and 83%, respectively. In an enterprise trace-based case study, CloudPD diagnosed anomalies within 30 seconds and with an accuracy of 77%, demonstrating its effectiveness in real-life operations.

show abstract