Multi-resource fair queueing for packet processing

@inproceedings{Ghodsi2012MultiresourceFQ,
  title={Multi-resource fair queueing for packet processing},
  author={Ali Ghodsi and Vyas Sekar and Matei A. Zaharia and Ion Stoica},
  booktitle={SIGCOMM '12},
  year={2012}
}
Middleboxes are ubiquitous in today's networks and perform a variety of important functions, including IDS, VPN, firewalling, and WAN optimization. These functions differ vastly in their requirements for hardware resources (e.g., CPU cycles and memory bandwidth). Thus, depending on the functions they go through, different flows can consume different amounts of a middlebox's resources. While there is much literature on weighted fair sharing of link bandwidth to isolate flows, it is unclear how… 
On Low Complexity Multi-Resource Packet Scheduling with Dominant Resource Fairness
TLDR
A new multi-resource fair queueing scheme that schedules packets in a manner similar to Elastic Round Robin is designed, which requires only O(1) work to schedule a packet and is simple enough to implement in practice.
Multi-resource generalized processor sharing for packet processing
TLDR
The fairness requirements of a queueing scheme are clarified and Dominant Resource Generalized Processor Sharing (DRGPS) is presented, a fluid flow-based fair queueing idealization that strictly realizes Dominant resource Fairness (DRF) at all times.
Multi-Resource Round Robin: A low complexity packet scheduler with Dominant Resource Fairness
TLDR
A new multi-resource fair queueing scheme that schedules packets in a way similar to Elastic Round Robin is designed, which requires only O(1) work to schedule a packet and is simple enough to implement in practice.
Low complexity multi-resource fair queueing with bounded delay
TLDR
This paper presents a new fair queueing algorithm, called Group Multi-Resource Round Robin (GMR3), that schedules packets in O(1) time, while achieving near-perfect fairness with a low scheduling delay bounded by a small constant.
On Fairness-Efficiency Tradeoffs for Multi-resource Packet Processing
  • Wei Wang, B. Liang, Baochun Li
  • Computer Science
    2013 IEEE 33rd International Conference on Distributed Computing Systems Workshops
  • 2013
TLDR
It is shown in this paper that there exists a fairnessefficiency tradeoff when multiple resources are scheduled, and how to design a packet scheduling algorithm to reinforce such a tradeoff is presented.
On the Fairness-Efficiency Tradeoff for Packet Processing with Multiple Resources
TLDR
Experimental results suggest that trading off a modest level of fairness can potentially improve the efficiency to the point where the system capacity is almost saturated.
ATFQ: A Fair and Efficient Packet Scheduling Method in Multi-Resource Environments
TLDR
A novel packet scheduling method, active time fairness queuing (ATFQ), for multi-resource environments that can maximize the resource utilization with the guarantee of fairness and demonstrate that flows get better service in many aspects under ATFQ.
Low-complexity multi-resource packet scheduling for network function virtualization
  • Xin Li, Chen Qian
  • Computer Science, Business
    2015 IEEE Conference on Computer Communications (INFOCOM)
  • 2015
TLDR
This paper designs a novel low-complexity and space-efficient packet scheduling algorithm called Myopia, which supports multi- resource environments such as network function virtualization and demonstrates, via theoretical analysis, prototype implementation, and simulations, that Myopia achieves multi-resource fairness at low cost with short packet delay.
MDFS: Deadline-Driven Flow Scheduling Scheme in Multi-Resource Environments
TLDR
This paper proposes multi-resource & deadline-driven flow scheduling (MDFS) to satisfy the deadline requirements of flows in multi- resource environments and greatly outperforms the performance of other scheduling schemes.
Improving Software Middleboxes and Datacenter Task Schedulers
TLDR
This master's thesis presents Sprayer, a system that uses packet spraying to load balance packets to cores in software middleboxes and Stateful Dominant Resource Fairness (SDRF), a task scheduling policy for datacenters that looks at past allocations and enforces fairness in the long run.
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 44 REFERENCES
Start-time fair queueing: a scheduling algorithm for integrated services packet switching networks
We present Start-time Fair Queuing (SFQ) algorithm that is computationally efficient, achieves fairness regardless of variation in a server capacity, and has the smallest fairness measure among all
Start-time fair queueing: a scheduling algorithm for integrated services packet switching networks
TLDR
This analysis demonstrates that SFQ is suitable for integrated services networks since it achieves low average as well as maximum delay for low-throughput applications and provides fairness, regardless of variation in server capacity, for throughput-intensive, flow-controlled data applications.
Efficient fair queueing using deficit round robin
TLDR
This paper describes a new approximation of fair queuing that achieves nearly perfect fairness in terms of throughput, requires only O(1) work to process a packet, and is simple enough to implement in hardware.
A generalized processor sharing approach to flow control in integrated services networks: the single-node case
TLDR
Worst-case bounds on delay and backlog are derived for leaky bucket constrained sessions in arbitrary topology networks of generalized processor sharing (GPS) servers and the effectiveness of PGPS in guaranteeing worst-case session delay is demonstrated under certain assignments.
WF/sup 2/Q: worst-case fair weighted fair queueing
  • J. R. Bennett, Hui Zhang
  • Computer Science
    Proceedings of IEEE INFOCOM '96. Conference on Computer Communications
  • 1996
TLDR
It has been proven that the delay bound provided by WFQ is within one packet transmission time of that provided by GPS, and a new packet approximation algorithm of GPS called worst-case fair weighted fair queueing (WF/sup 2/Q) is proposed.
Improved Forwarding Architecture and Resource Management for Multi-Core Software Routers
TLDR
An improved forwarding architecture for software routers that enhances parallelism by exploiting hardware classification and multi-queue support, already available in recent commodity network interface cards is introduced.
WF 2 Q : Worst-case Fair Weighted Fair
TLDR
It is argued that there could be large discrepancies between the services provided by the packet WFQ system and the uid GPS system, which will adversely affect many congestion control algorithms that rely on services similar to those provided by GPS.
A self-clocked fair queueing scheme for broadband applications
  • S. J. Golestani
  • Computer Science
    Proceedings of INFOCOM '94 Conference on Computer Communications
  • 1994
TLDR
The author proves that the scheme possesses the desired fairness property and is nearly optimal, in the sense that the maximum permissible disparity among the normalized services offered to the backlogged sessions is never more than two times the corresponding figure in any packet-based queueing system.
No justified complaints: on fair sharing of multiple resources
TLDR
This work provides a new definition for the simultaneous fair allocation of multiple continuously-divisible resources that is called bottleneck-based fairness (BBF), and shows that BBF has several desirable properties such as providing an incentive for sharing, and also promotes high overall utilization of resources.
Lottery and stride scheduling: flexible proportional-share resource management
TLDR
This thesis presents flexible abstractions for specifying resource management policies, together with efficient mechanisms for implementing those abstractions, including both randomized and deterministic algorithms that provide proportional-share control over resource consumption rates.
...
1
2
3
4
5
...