摘要：Background: Online monitoring is of great importance to datacenter applications. Since a datacenter usually hosts a large number of applications, it is cost-effective to provide a generic and reusable application-monitoring platform instead of creating monitoring facilities from scratch for each application. However, it is of great challenge to fit diversified monitoring requirements of various applications by a unified platform. Material and Methods: This study proposes such a monitoring platform named CloudAmulet. It can effectively collect, aggregate, analyze and visualize various application-level monitoring data. To achieve this goal, this platform is designed to be a highly configurable monitoring infrastructure whose behavior can be customized by application-specific meta entities, including application metric meta data, visualization meta data and data aggregation rules. By dynamically loading different meta entities, CloudAmulet can support the monitoring of different applications. Results: CloudAmulet has been successfully applied to a set of real production systems. The case study based on a real-life datacenter application illustrates that by promoting software reuse, our approach can reduce nearly 85% lines of code in comparison with realizing the application monitoring capability from scratch. Conclusion: CloudAmulet significantly promotes the software reuse in datacenter application monitoring and efficiently reduces the effort in enabling the online monitoring of those applications.
