Large-scale parallel server system with multi-component jobs

DOI10.1007/S11134-021-09686-YzbMATH Open1478.90022arXiv2006.11256OpenAlexW3125609401MaRDI QIDQ2052940FDOQ2052940

Authors: V. Shneer, Alexander L. Stolyar 

Publication date: 29 November 2021

Published in: Queueing Systems (Search for Journal in Brave)

Abstract: A broad class of parallel server systems is considered, for which we prove the steady-state asymptotic independence of server workloads, as the number of servers goes to infinity, while the system load remains sub-critical. Arriving jobs consist of multiple components. There are multiple job classes, and each class may be of one of two types, which determines the rule according to which the job components add workloads to the servers. The model is broad enough to include as special cases some popular queueing models with redundancy, such as cancel-on-start and cancel-on-completion redundancy. Our analysis uses mean-field process representation and the corresponding mean-field limits. In essence, our approach relies almost exclusively on three fundamental properties of the model: (a) monotonicity, (b) work conservation, (c) the property that, on average, "new arriving workload prefers to go to servers with lower workloads."

Full work available at URL: https://arxiv.org/abs/2006.11256

Recommendations

• Parallel Server Systems with Cancel-on-Completion Redundancy
• Delay asymptotics and bounds for multitask parallel jobs
• On stability and performance of parallel processing systems
• Uniform stability of some large-scale parallel server networks
• Systems with large flexible server pools: instability of ``natural load balancing

zbMATH Keywords

asymptotic independencereplicationredundancysteady-statelarge-scale service systemscancel on completioncancel on startload distribution and balancingmulti-component jobs

Mathematics Subject Classification ID

Queueing theory (aspects of probability theory) (60K25) Stochastic network models in operations research (90B15)

Cites Work

• Queueing system with selection of the shortest of two queues: An asymptotic approach
• Martingale proofs of many-server heavy-traffic limits for Markovian queues
• Asymptotic independence of queues under randomized load balancing
• On the stability of a partially accessible multi-station queue with state-dependent routing
• Stability of join the shortest queue networks
• Title not available (Why is that?)
• Pull-based load distribution among heterogeneous parallel servers: the case of multiple routers
• Pull-based load distribution in large-scale heterogeneous service systems
• Redundancy-\(\mathbf{d}\): the power of \(\mathbf{d}\) choices for redundancy

Cited In (7)

• Parallel Server Systems with Cancel-on-Completion Redundancy
• Asymptotic independence of servers' activity in queueing systems with limited resource pooling
• Queue-length-aware dispatching in large-scale heterogeneous systems
• Join-Up-To\((m)\): improved hyperscalable load balancing
• Redundancy scheduling with scaled Bernoulli service requirements
• Job replication on multiserver systems
• Delay asymptotics and bounds for multitask parallel jobs

This page was built for publication: Large-scale parallel server system with multi-component jobs

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2052940)