Research On Local Storage Based Resource Consolidation And Prediction In Cloud

Server consolidation is a useful solution aiming at cost-efficiency and high resource utilization of data centers and clusters.Nowadays,as the data-intensive and I/O intensive applications are widely used,more attention is paid to the local storage based clouds which can offer much better I/O performance at relatively low price compared with shared storage.With the advent of outsourced computing and storage in 58 the form of public clouds,most local storage based cloud services as we mentioned above are running relational database services.It is now common for a single data center to deploy hundreds or thousands of individual relational database management systems(DBMSs).For example,one large telecommunications company with which we are familiar has more than 20,000 DBMS instances deployed in its internal infrastructure.Often times,each database is deployed on a dedicated server,with the machine provisioned for the peak load that is expected to be placed on the database.In practice,most databases have natural ebbs and flows,occasional unexpected events,and a certain degree of statistical correlation(or lack of correlation)with other databases in the same data center.Over-provisioning and uncorrelated loads provide the opportunity to consolidate servers onto fewer physical machines.However,it will obviously increase the migration cost(e.g.energy and time).Meanwhile,there is few suitable resource demand estimation method for local storage based clouds at present,which plays an important role in system's migration efficiency.And we find out that in this specific storage architecture,almost all the existing server consolidation algorithms do not have suitable resource demand estimation method and live migration scheme.To solve this problems,this paper designs and implements C3,a cloud architecture for local storage,Combining Three(C3)significant modules: prediction,consolidation and migration.It was proved in statistical analysis that ARIMA may be the most suitable prediction model for the server workload,which motivates us to propose the resource estimation predictor.Also,we improve the existing consolidation method by adjusting the sorting index and fit degree during migration.Then,we propose a live migration scheme for local storage environment as the third module of C3.We conduct extensive experiments using real-world traces from Google to validate the effectiveness and superiority of our proposed algorithm.