Theoretical and Experimental Evaluation of the Two-Level Processor Sharing Discipline for TCP Flows

Marin, Andrea; Rossi, Sabina; Sottana, Matteo; Zen, Carlo

doi:10.1109/mascots.2019.00020

“…When the service rate is constant in these cases, multi-level scheduling is a well-known technique to reduce the mean response time in systems with highly variable job sizes. It can provide much lower response time than the Processor Sharing (PS) discipline, especially for heavy-tailed service time distributions [1,2,8,10].…”

Section: Copyright Is Held By Author/owner(s)mentioning

confidence: 99%

Frequency scaling in multilevel queues

Elahi

¹

,

Marin

²

,

Rossi

³

et al. 2021

SIGMETRICS Perform. Eval. Rev.

Self Cite

0

View full text Add to dashboard Cite

In this paper, we study a variant of PS+PS multilevel scheduling, which we call the PS+IS queue. Specifically, we use Processor Sharing (PS) at both queues, but with linear frequency scaling on the second queue, so that the latter behaves like an Infinite Server (IS) queue. The goals of the system are low response times for small jobs in the first queue, and reduced power consumption for large jobs in the second queue. The novelty of our model includes the frequency scaling at the second queue, and the batch arrival process at the second queue induced by the busy period structure of the first queue which has strictly higher priority. We derive a numerical solution for the PS+IS queueing system in steady-state, and then study its properties under workloads obtained from fitting of TCP flow traces. The simulation results confirm the e

show abstract

A Matlab Toolkit for the Analysis of Two-Level Processor Sharing Queues

Marin

¹

,

Rossi

²

,

Zen

³

2020

Quantitative Evaluation of Systems

0

View full text Add to dashboard Cite

Frequency scaling in multilevel queues

Elahi

¹

,

Marin

²

,

Rossi

³

et al. 2020

Performance Evaluation

View full text Add to dashboard Cite

In this paper, we study a variant of PS+PS multilevel scheduling, which we call the PS+IS queue. Specifically, we use Processor Sharing (PS) at both queues, but with linear frequency scaling on the second queue, so that the latter behaves like an Infinite Server (IS) queue. The goals of the system are low response times for small jobs in the first queue, and reduced power consumption for large jobs in the second queue. The novelty of our model includes the frequency scaling at the second queue, and the batch arrival process at the second queue induced by the busy period structure of the first queue which has strictly higher priority. We derive a numerical solution for the PS+IS queueing system in steady-state, and then study its properties under workloads obtained from fitting of TCP flow traces. The simulation results confirm the e cacy of the PS+IS model. This article is an introduction to our longer paper in [5].

show abstract

Theoretical and Experimental Evaluation of the Two-Level Processor Sharing Discipline for TCP Flows

Cited by 3 publications

References 24 publications

Frequency scaling in multilevel queues

Frequency scaling in multilevel queues

A Matlab Toolkit for the Analysis of Two-Level Processor Sharing Queues

Frequency scaling in multilevel queues

Contact Info

Product

Resources

About