Currently, the allocation of applications to clouds is usually done on an ad-hoc, per-application basis, which is not ideal as it lacks rigour and auditability.
The system we consider is based on a centralized network dispatcher which controls the allocation of applications to servers, the request volumes at various servers and the scheduling policy at each server.
A set of high-level directives permits users to specify the allocation needs of application objects; a dynamic load-balancing tool – part of the environment run-time support – uses the user-level allocation directives to tune its behaviour.
A fair allocation of utility (application-layer performance) is essential in providing QoS (Quality of Service) guarantee.
We show that use of Lagrangian optimization provides a fast, elegant, and, for convex problems, optimal solution to the allocation of energy across applications as they enter and leave the system, even if the exact sequence and timing of their entrances and exits is not known.
Linked to this should be clarity in allocation and application of their respective roles, as ignoring this can exacerbate confusion about how vertical managers should engage with horizontal management structures (18).
For ease of explanation, we assume that all applications considered for resource allocation have the same number of application tiers.
The authors describe a system that is able to self-optimize the allocation of resources to different application environments.
For example, cloud SPs can study the effect of dynamically changing resource allocations to applications at resource allocation intervals of 30 min within a planning horizon of 24 h.
This work addresses the problem of finding a robust initial allocation of resources to strings of applications that is able to absorb some level of unknown input workload increase without rescheduling.
