As the web-server based business is rapidly developed and popularized, how to evaluate and improve the reliability of web-servers has been extremely important. Although a large num- ber of software reliability growth ...As the web-server based business is rapidly developed and popularized, how to evaluate and improve the reliability of web-servers has been extremely important. Although a large num- ber of software reliability growth models （SRGMs）, including those combined with multiple change-points （CPs）, have been available, these conventional SRGMs cannot be directly applied to web soft- ware reliability analysis because of the complex web operational profile. To characterize the web operational profile precisely, it should be realized that the workload of a web server is normally non-homogeneous and often observed with the pattern of random impulsive shocks. A web software reliability model with random im- pulsive shocks and its statistical analysis method are developed. In the proposed model, the web server workload is characterized by a geometric Brownian motion process. Based on a real data set from IIS server logs of ICRMS website （www.icrms.cn）, the proposed model is demonstrated to be powerful for estimating impulsive shocks and web software reliability.展开更多
Cloud monitoring is of a source of big data that are constantly produced from traces of infrastructures,platforms, and applications. Analysis of monitoring data delivers insights of the system＇s workload and usage pa...Cloud monitoring is of a source of big data that are constantly produced from traces of infrastructures,platforms, and applications. Analysis of monitoring data delivers insights of the system＇s workload and usage pattern and ensures workloads are operating at optimum levels. The analysis process involves data query and extraction, data analysis, and result visualization. Since the volume of monitoring data is big, these operations require a scalable and reliable architecture to extract, aggregate, and analyze data in an arbitrary range of granularity. Ultimately, the results of analysis become the knowledge of the system and should be shared and communicated. This paper presents our cloud service architecture that explores a search cluster for data indexing and query. We develop REST APIs that the data can be accessed by different analysis modules. This architecture enables extensions to integrate with software frameworks of both batch processing（such as Hadoop） and stream processing（such as Spark） of big data. The analysis results are structured in Semantic Media Wiki pages in the context of the monitoring data source and the analysis process. This cloud architecture is empirically assessed to evaluate its responsiveness when processing a large set of data records under node failures.展开更多
基金supported by the International Technology Cooperation Project of Guizhou Province(QianKeHeWaiGZi[2012]7052)the National Scientific Research Project for Statistics(2012LZ054)
文摘As the web-server based business is rapidly developed and popularized, how to evaluate and improve the reliability of web-servers has been extremely important. Although a large num- ber of software reliability growth models （SRGMs）, including those combined with multiple change-points （CPs）, have been available, these conventional SRGMs cannot be directly applied to web soft- ware reliability analysis because of the complex web operational profile. To characterize the web operational profile precisely, it should be realized that the workload of a web server is normally non-homogeneous and often observed with the pattern of random impulsive shocks. A web software reliability model with random im- pulsive shocks and its statistical analysis method are developed. In the proposed model, the web server workload is characterized by a geometric Brownian motion process. Based on a real data set from IIS server logs of ICRMS website （www.icrms.cn）, the proposed model is demonstrated to be powerful for estimating impulsive shocks and web software reliability.
基金supported by the Discovery grant No.RGPIN 2014-05254 from Natural Science&Engineering Research Council(NSERC),Canada
文摘Cloud monitoring is of a source of big data that are constantly produced from traces of infrastructures,platforms, and applications. Analysis of monitoring data delivers insights of the system＇s workload and usage pattern and ensures workloads are operating at optimum levels. The analysis process involves data query and extraction, data analysis, and result visualization. Since the volume of monitoring data is big, these operations require a scalable and reliable architecture to extract, aggregate, and analyze data in an arbitrary range of granularity. Ultimately, the results of analysis become the knowledge of the system and should be shared and communicated. This paper presents our cloud service architecture that explores a search cluster for data indexing and query. We develop REST APIs that the data can be accessed by different analysis modules. This architecture enables extensions to integrate with software frameworks of both batch processing（such as Hadoop） and stream processing（such as Spark） of big data. The analysis results are structured in Semantic Media Wiki pages in the context of the monitoring data source and the analysis process. This cloud architecture is empirically assessed to evaluate its responsiveness when processing a large set of data records under node failures.
