CL-SLAM: Cross-Layer SLA Monitoring Framework for Cloud Service-Based Applications

Modern applications are increasingly being composed from multiple components that require and consume services at dierent layers of the cloud stack. The diverse, dynamic and unpredictable nature of both cloud services and application workloads makes quality-assured provision of such cloud service-based applications (CSBAs) a major challenge. While elasticity and autoscaling gives CSBA providers the ability to scale cloud resources on-demand, they require a comprehensive, system-wide view of the application performance in order to make timely, cost-eective and performanceecient scaling decisions. In this paper, we propose, develop and validate CL-SLAM a Cross-Layer SLA Monitoring Framework for CSBAs. Its main features include (a) realtime, fine-grained visibility into CSBA performance, (b) visual descriptive analytics to identify correlations and interdependencies between cross-layer performance metrics, (c) temporal profiling of CSBA performance, (d) proactive monitoring, detection and root-cause analysis of SLA violation, and (e) support for both reactive and proactive adaptation in support of quality-assured CSBA provision. We validate our approach through a prototype implementation.