Hierarchical Deficit Round-Robin Packet Scheduling Algorithm

Chen, Min-Xiou; Liu, Shih-Hao

doi:10.1007/978-3-642-35452-6_43

Cited by 4 publications

(2 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A scheduler requires a time management function to implement the RR architecture and requires a tick timer [14]. The time slice is proportional to the period of clock ticks [8].…”

Section: Rr Algorithmmentioning

confidence: 99%

Multi-queue CPU Process Prioritization using a Dynamic Quantum Time Algorithm Compared with Varying Time Quantum and Round-Robin Algorithms

Mohammed¹,

AbdulMajid²,

Mustafa³

2016

IJCA

View full text Add to dashboard Cite

In Round-Robin Scheduling, the quantum time is static and tasks are scheduled such that no process uses CPU time more than one slice time each cycle. If quantum time is too large, the response time of the processes will not be tolerated in an interactive environment. If quantum the time is too small, unnecessary frequent context switch may occur. Consequently, overheads result in fewer throughputs. In this study, we propose a priority multi queues algorithm with dynamic quantum time. The algorithm uses multi queues with different quantum times for the processes. The quantum times for the processes are depending on the priorities which in turn depending on the burst times of the processes. The proposed algorithm has been compared with varying time quantum algorithm which already exist to improve the original round robin algorithm. With proposed algorithm, the simple Round-Robin algorithm has been improved by about 35%. By controlling quantum time, we experience fewer context switches and shorter waiting and turnaround times, thereby obtaining higher throughput.

show abstract

“…A scheduler requires a time management function to implement the RR architecture and requires a tick timer [14]. The time slice is proportional to the period of clock ticks [8].…”

Section: Rr Algorithmmentioning

confidence: 99%

Multi-queue CPU Process Prioritization using a Dynamic Quantum Time Algorithm Compared with Varying Time Quantum and Round-Robin Algorithms

Mohammed¹,

AbdulMajid²,

Mustafa³

2016

IJCA

View full text Add to dashboard Cite

show abstract

“…This results in good fairness properties, but rounds grow prohibitively large which may result in excessive delays between packet transmissions for some classes. Other efforts in this direction, e.g., [14], [15] make scheduling decisions in multiple stages, one per level in the class hierarchy, and thus inherit the drawbacks of HPFQ.…”

Section: Introductionmentioning

confidence: 99%

A Round-Robin Packet Scheduler for Hierarchical Max-Min Fairness

Luangsomboon,

Liebeherr

2021

Preprint

View full text Add to dashboard Cite

Hierarchical link sharing addresses the demand for fine-grain traffic control at multiple levels of aggregation. At present, packet schedulers that can support hierarchical link sharing are not suitable for an implementation at line rates, and deployed schedulers perform poorly when distributing excess capacity to classes that need additional bandwidth. We present HLS, a packet scheduler that ensures a hierarchical max-min fair allocation of the link bandwidth. HLS supports minimum rate guarantees and isolation between classes. Since it is realized as a nonhierarchical round-robin scheduler, it is suitable to operate at high rates. We implement HLS in the Linux kernel and evaluate it with respect to achieved rate allocations and overhead. We compare the results with those obtained for CBQ and HTB, the existing scheduling algorithms in Linux for hierarchical link sharing. We show that the overhead of HLS is comparable to that of other classful packet schedulers.

show abstract

HLS: A Packet Scheduler for Hierarchical Fairness

Luangsomboon

Liebeherr

2021

2021 IEEE 29th International Conference on Network Protocols (ICNP)

View full text Add to dashboard Cite

Traffic from distributed training of machine learning (ML) models makes up a large and growing fraction of the traffic mix in enterprise data centers. While work on distributed ML abounds, the network traffic generated by distributed ML has received little attention. Using measurements on a testbed network, we investigate the traffic characteristics generated by the training of the ResNet-50 neural network with an emphasis on studying its shortterm burstiness. For the latter we propose metrics that quantify traffic burstiness at different time scales. Our analysis reveals that distributed ML traffic exhibits a very high degree of burstiness on short time scales, exceeding a 60:1 peak-to-mean ratio on time intervals as long as 5 ms. We observe that training software orchestrates transmissions in such a way that burst transmissions from different sources within the same application do not result in congestion and packet losses. An extrapolation of the measurement data to multiple applications underscores the challenges of distributed ML traffic for congestion and flow control algorithms.

show abstract

Hierarchical Deficit Round-Robin Packet Scheduling Algorithm

Cited by 4 publications

References 9 publications

Multi-queue CPU Process Prioritization using a Dynamic Quantum Time Algorithm Compared with Varying Time Quantum and Round-Robin Algorithms

Multi-queue CPU Process Prioritization using a Dynamic Quantum Time Algorithm Compared with Varying Time Quantum and Round-Robin Algorithms

A Round-Robin Packet Scheduler for Hierarchical Max-Min Fairness

HLS: A Packet Scheduler for Hierarchical Fairness

Contact Info

Product

Resources

About