Hi everybody! I am currently involving in a research project to develop an open resource manager based on intelligent algorithms to manage resources within cloud platforms.
Under my proposed hypothesis, an intelligent scheduler is continuously regulating the distribution of resources at the end of discrete control intervals. The scheduler needs to formulate a strategy for doing this regulation by either adding/removing resources in forms of virtual machines to the running applications, or adjusting the utilization levels ( fractions of CPU and RAM usage) of the running virtual machines or adjust the allocation of virtual machines to the active physical machines (by live migration). Surely, it is up to the scheduler to use one or combinations of the above approaches in order to guarantee the optimal status of the running configuration (i.e. combinations of active virtual machines and physical machines). So, my questions are as follows: How auto scaling in Scalr differs from auto scaling in the above mentioned scenario? In order to utilize Scalr to implement the above mentioned model, Shall I concentrate on Scripting engine? Or Shall I tweak the original modules responsible on auto scaling in Scalr? Or Shall I add additional functional modules to cooperate with the original ones in Scalr to implement the above mentioned approach? What kind of coding languages I shall consider to include the source code of the intelligent scheduler into Scalr environment? I will be more than grateful if you can clarify the above mentioned questions as much as possible. -- You received this message because you are subscribed to the Google Groups "scalr-discuss" group. To post to this group, send email to [email protected]. To unsubscribe from this group, send email to [email protected]. For more options, visit this group at http://groups.google.com/group/scalr-discuss?hl=en.
