Systems and methods of managing computational resources

A controller for managing computational resources, comprising:

• processing circuitry;
• memory containing instructions executable by the processing circuitry whereby the controller is operative to:
• dynamically distribute computational resource shares among sequential services that are mapped to one or more processors, wherein each sequential service corresponds to an execution step of a remote application and wherein a service chain comprises at least one sequential service, based on estimated and predetermined tail latencies and average execution times of each sequential service in the service chain as well as the service chain such that the latencies are met, and wherein one or more service chains are executed contemporaneously;
• wherein, for each service chain, dynamically distributing the computational resource shares comprises:
• determining a statistical distribution of a workload for each service of the service chain based on the computational resource shares, and on current execution times for the services of the service chain for a current execution of the service chain;
• and
• allocating the computational resource shares for the services of the service chain for a next execution of the service chain based on the statistical distributions and on the estimated and predetermined tail latencies of the service chain.

A non-transitory computer readable recording medium storing a computer program product for managing computational resources, the computer program product comprising software instructions which, when run on processing circuitry of a controller, causes the controller to:

• dynamically distribute computational resource shares among sequential services that are mapped to one or more processors, wherein each sequential service corresponds to an execution step of a remote application and wherein a service chain comprises at least one sequential service, based on estimated and predetermined tail latencies and average execution times of each sequential service in the service chain as well as the service chain such that the latencies are met, and wherein one or more service chains are executed contemporaneously;
• wherein dynamically distributing the computational resource shares comprises, for each service chain:
• determining a statistical distribution of a workload for each service of the service chain based on the computational resource shares, and on current execution times for the services of the service chain for a current execution of the service chain;
• and
• allocating the computational resource shares for the services of the service chain for a next execution of the service chain based on the statistical distributions and on the estimated and predetermined tail latencies of the service chain.