Steady-State Behavior of Some Load Balancing Mechanisms in Cloud Storage Systems
From MaRDI portal
Queueing theory (aspects of probability theory) (60K25) Applications of queueing theory (congestion, allocation, storage, traffic, etc.) (60K30) Interacting random processes; statistical mechanics type models; percolation theory (60K35) Performance evaluation, queueing, and scheduling in the context of computer systems (68M20) Queues and service in operations research (90B22) Sensitivity, stability, parametric optimization (90C31)
Abstract: In large storage systems, files are often coded across several servers to improve reliability and retrieval speed. We consider a system of servers storing files using a Maximum Distance Separable code (cf. cite{li2016mean}). Specifically, each file is stored in equally sized pieces across servers such that any pieces can reconstruct the original file. File requests are routed using the Batch Sampling routing scheme. I.e. when a request for a file is received, a centralized dispatcher routes the job into the -shortest queues among the for which the corresponding server contains a piece of the file being requested. We study the long time behavior of this class of load balancing mechanisms. In particular, it is shown that the ODE system that describes the mean field limit of the occupancy measure process has a unique fixed point which is stable. This fixed point corresponds to a distribution on of queue lengths with tails that decay super-exponentially. Upper and lower bounds on the decay rate are provided. Finally, we show that the unique invariant measure of the Markov occupancy measure process converges to the Dirac measure concentrated at the unique fixed point of the ODE system, establishing the interchangeability of the and limits.
This page was built for publication: Steady-State Behavior of Some Load Balancing Mechanisms in Cloud Storage Systems
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6296211)
