Optimizing runtime performance of an application workload by minimizing network input/output communications between virtual machines on different clouds in a hybrid cloud topology during cloud bursting

摘要

A method, system and computer program product for optimizing runtime performance of an application workload. Network input/output (I/O) operations between virtual machines of a pattern of virtual machines servicing the application workload in a private cloud are measured over a period of time and depicted in a histogram. A score is generated for each virtual machine or group of virtual machines in the pattern of virtual machines based on which range in the ranges of I/O operations per seconds (IOPS) depicted in the histogram has the largest sample size and the number of virtual machines in the same pattern that are allowed to be in the public cloud. In this manner, the runtime performance of the application workload is improved by minimizing the network input/output communications between the two cloud environments by migrating those virtual machine(s) or group(s) of virtual machines with a score that exceeds a threshold value.

主权项

1. A computer program product for optimizing runtime performance of an application workload in a hybrid cloud topology, the computer program product comprising a computer readable storage medium having program code embodied therewith, the program code comprising the programming instructions for:
measuring network input/output (1/0) operations between virtual machines of a pattern of virtual machines servicing said application workload in a private cloud over a period of time; generating a histogram of I/O usage for each of said plurality of virtual machines or for each group of said plurality of groups of virtual machines in said pattern of virtual machines comprising groups of different ranges of I/O operations per second using said measured network I/O operations; generating a score for each of a plurality of virtual machines or for each group of a plurality of groups of virtual machines in said pattern of virtual machines used to service said application workload based on a highest number of samples within a range of I/O operations per second using said measured network I/O operations and a number of virtual machines in said pattern of virtual machines that are allowed to be in a public cloud; generating said score for each of said plurality of virtual machines or for each group of said plurality of groups of virtual machines in said pattern of virtual machines used to service said application workload based on which group of said groups of different ranges of I/O operations per second has a largest sample size and said number of virtual machines in said pattern of virtual machines that are allowed to be in said public cloud; ranking each of said plurality of virtual machines or each group of said plurality of groups of virtual machines in said pattern of virtual machines based on said score; and migrating one or more of said plurality of virtual machines or one or more groups of said plurality of groups of virtual machines in said pattern of virtual machines to said public cloud to service said application workload in response to said score for said one or more of said plurality of virtual machines or for said one or more groups of said plurality of groups of virtual machines in said pattern of virtual machines exceeding a threshold value.