Heavy-tailed limits for medium size jobs and comparison scheduling
From MaRDI portal
(Redirected from Publication:839865)
Abstract: We study the conditional sojourn time distributions of processor sharing (PS), foreground background processor sharing (FBPS) and shortest remaining processing time first (SRPT) scheduling disciplines on an event where the job size of a customer arriving in stationarity is smaller than exactly k>=0 out of the preceding m>=k arrivals. Then, conditioning on the preceding event, the sojourn time distribution of this newly arriving customer behaves asymptotically the same as if the customer were served in isolation with a server of rate (1-
ho)/(k+1) for PS/FBPS, and (1-
ho) for SRPT, respectively, where
ho is the traffic intensity. Hence, the introduced notion of conditional limits allows us to distinguish the asymptotic performance of the studied schedulers by showing that SRPT exhibits considerably better asymptotic behavior for relatively smaller jobs than PS/FBPS. Inspired by the preceding results, we propose an approximation to the SRPT discipline based on a novel adaptive job grouping mechanism that uses relative size comparison of a newly arriving job to the preceding m arrivals. Specifically, if the newly arriving job is smaller than k and larger than m-k of the previous m jobs, it is routed into class k. Then, the classes of smaller jobs are served with higher priorities using the static priority scheduling. The good performance of this mechanism, even for a small number of classes m+1, is demonstrated using the asymptotic queueing analysis under the heavy-tailed job requirements. We also discuss refinements of the comparison grouping mechanism that improve the accuracy of job classification at the expense of a small additional complexity.
Recommendations
- Preventing Large Sojourn Times Using SMART Scheduling
- Is tail-optimal scheduling possible?
- On the average sojourn time under \(M/M/1/\)SRPT
- Heavy traffic scaling limits for shortest remaining processing time queues with heavy tailed processing time distributions
- Queues with equally heavy sojourn time and service requirement distributions
Cites work
- scientific article; zbMATH DE number 47258 (Why is no real title available?)
- scientific article; zbMATH DE number 3562235 (Why is no real title available?)
- scientific article; zbMATH DE number 1466126 (Why is no real title available?)
- scientific article; zbMATH DE number 3322728 (Why is no real title available?)
- A large-deviations analysis of the GI/GI/1 SRPT queue
- Asymptotic loss probability in a finite buffer fluid queue with heterogeneous heavy-tailed on-off processes
- Grouped distributed queues, distributed queue, proportional share multiprocessor scheduling
- Handling load with less stress
- Large Deviation Analysis of Subexponential Waiting Times in a Processor-Sharing Queue
- Largest weighted delay first scheduling: Large deviations and optimality
- Letter to the Editor—A Proof of the Optimality of the Shortest Remaining Processing Time Discipline
- On the exact asymptotics of the busy period in GI/G/1 queues
- On the tails of waiting-time distributions
- Preventing Large Sojourn Times Using SMART Scheduling
- Reduced-load equivalence and induced burstiness in GPS queues with long-tailed traffic flows
- Scheduling strategies and long-range dependence
- Sojourn time asymptotics in the M/G/1 processor sharing queue
- Subexponential asymptotics of a Markov-modulated random walk with queueing applications
- Tail probabilities for non-standard risk and queueing processes with subexponential jumps
- The Queue M/G/1 with the Shortest Remaining Processing Time Discipline
Cited in
(2)
This page was built for publication: Heavy-tailed limits for medium size jobs and comparison scheduling
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q839865)
