RR-LQD: A novel scheduling algorithm for CICQ switching fabrics

Yun, Zi; Peng, Laixian; Zhao, Wei; Tian, Chao

doi:10.1109/apcc.2009.5375470

Cited by 3 publications

(6 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…So far, there have been many scheduling algorith ms for CICQ switches and can be classified into three categories. One category is Round Robin (RR) based algorithm, such as RR_RR [6] and RR-LQD [9]. They use different pointer updating mechanisms to perform scheduling and achieve 100% throughput under uniform traffic.…”

Section: Introductionmentioning

confidence: 99%

A Novel High Performance Scheduling Algorithm for Crosspoint Buffered Crossbar Switches

Wang¹,

Wang²,

Li³

et al. 2015

Proceedings of the International Conference on Computer Information Systems and Industrial Applications

View full text Add to dashboard Cite

Crosspoint buffered crossbar switches have gained much attention due to simple distributed scheduling algorithms. However, almost all the algorithms proposed for buffered crossbar switches either have unsatisfactory scheduling performance under non-uniform traffic or poor service fairness between input traffic flows. In order to overcome the disadvantages, in this paper we propose a novel efficient scheduling algorithm named MCQF_RR, which takes advantage of the combined information about queue length and service waiting time of queues to perform scheduling, in order to ensure good service fairness. Simulation results show that the proposed MCQF_RR demonstrates good delay performance comparable to existing efficient algorithms under various admissible traffic patterns, while achieve better service fairness under extreme nonuniform traffic.

show abstract

Section: Introductionmentioning

confidence: 99%

A Novel High Performance Scheduling Algorithm for Crosspoint Buffered Crossbar Switches

Wang¹,

Wang²,

Li³

et al. 2015

Proceedings of the International Conference on Computer Information Systems and Industrial Applications

View full text Add to dashboard Cite

show abstract

“…However, it performs unstably under nonuniform traffic. Many improvements for the performance inefficiency have been made, such as Round Robin with Adaptable-size Frame (RR-AF) [21], Differential Round Robin (DRR) [22] and Round Robin-Longest Queue Detecting (RR-LQD) [23]. The basic idea of them is based on different pointer updating mechanisms to ensure efficient service of long queues and service fairness of short queues.…”

Section: Related Workmentioning

confidence: 99%

“…• RR-LQD [23], another Round Robin-based scheduling algorithm, where a different pointer updating policy is used in input scheduling, for its delay performance approximate to LQF RR under some non-uniform traffic and low time complexity of O(1).…”

Section: Simulation Settingsmentioning

confidence: 99%

Novel High Performance Scheduling Algorithms for Crosspoint Buffered Crossbar Switches

Wang

et al. 2015

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

SUMMARYThe crossbar-based switch fabric is widely used in today's high performance switches, due to its internally nonblocking and simply implementation properties. Usually there are two main switching architectures for crossbar-based switch fabric: internally bufferless crossbar switch and crosspoint buffered crossbar switch. As internally bufferless crossbar switch requires a complex centralized scheduler which limits its scalability to high speeds, crosspoint buffered crossbar switch has gained more attention because of its simpler distributed scheduling algorithm and better switching performance. However, almost all the scheduling algorithms proposed previously for crosspoint buffered crossbar switch either have unsatisfactory scheduling performance under non-uniform traffic patterns or show poor service fairness between input traffic flows. In order to overcome the disadvantages of existing algorithms, in this paper we propose two novel high performance scheduling algorithms named MCQF RR and IMCQF RR for crosspoint buffered crossbar switches. Both algorithms have a time complexity of O(log N), where N is the number of input/output ports of the switch. MCQF RR takes advantage of the combined weight information about queue length and service waiting time of input queues to perform scheduling. In order to further reduce the scheduling complexity and make it feasible for high speed switches, IMCQF RR uses the compressed queue length information instead of original queue length information to schedule cells in input VOQs. Simulation results show that our novel scheduling algorithms MCQF RR and IMCQF RR can demonstrate excellent delay performance comparable to existing high performance scheduling algorithms under both uniform and non-uniform traffic patterns, while maintain good service fairness performance under severe non-uniform traffic patterns.

show abstract

“…external link speed equals the internal speed of the switch, so it is more proper for fast implementation because it minimizes prerequisite for memory data transmission, where at most one packet is sent or received by an input/output port per a time slot [5], [6]. Iterative algorithms are widely used for the switches that use input queuing [7], [8]. The switch performance is affected significantly by the algorithm of scheduling that can be used for switch arbitration.…”

mentioning

confidence: 99%

“…In this paper, our focus is on some of existing efficient algorithms that depend on the pointer updating schema, including PIM [7], iSLIP [11], SSRR [12], SRRR [14], and CHRF [4] algorithms. We evaluate their performances and compare them to the proposed new algorithm called the "Single Bit Request Grant" (SBRG) algorithm.…”

mentioning

confidence: 99%

The Single Bit Request Grant (SBRG) Scheduling Algorithm for Input-Queued ATM Switches

Said

El-Saghir

El-Fishawy

2020

Menoufia Journal of Electronic Engineering Research

View full text Add to dashboard Cite

In this paper, we propose an efficient singleiteration single-bit request scheduling algorithm for input-queued ATM switches that based on a new arbitration technique called the Single Bit Request Grant (SBRG) algorithm. The operation of the SBRG depends on the concept known as "the preferred inputoutput pairs first", and the arbitration requests starts from switch output ports to reduce the number of issued request signals. Compared to other single-iteration algorithms, simulation results show that the SBRG maximizes the match size and improves the switch delay/throughput performance, especially when the load increases. Also, the proposed algorithm reduces the complexity of some of the existing algorithms by decreasing the number of input-output transferred messages, and by the absence of any encoding/decoding mechanism that can be used in some existing algorithms to reduce the size of request signals to one bit. Keywords-Input-queued ATM switch, single iteration scheduling algorithm, single-bit request scheduling algorithm. 1 1.. I In nt tr ro od du uc ct ti io on n Cloud computing architectures provide users with access to applications and services stay in shared server domains through the Internet [1], [2]. IP traffic is transferred in huge amounts between users and server domains, and among too many servers in each domain. Most server domains have storage area networks. These networks facilitate data transfer among disk matrices and the hundreds of servers within different data centers. Networks within data centers have many types, and they must use switches that are characterized by their high speed and low latency to achieve efficient data communication among the elements of these networks [3], [4]. There are many types of switch architectures that are used for data communications in ATM networks. The traditional output queuing switches can achieve a 100% throughput under any traffic load, but it requires high internal speed, which makes it impractical to be built in hardware, especially for large port numbers. In contrast, the switches that based on input queuing operates with an

show abstract

RR-LQD: A novel scheduling algorithm for CICQ switching fabrics

Cited by 3 publications

References 9 publications

A Novel High Performance Scheduling Algorithm for Crosspoint Buffered Crossbar Switches

A Novel High Performance Scheduling Algorithm for Crosspoint Buffered Crossbar Switches

Novel High Performance Scheduling Algorithms for Crosspoint Buffered Crossbar Switches

The Single Bit Request Grant (SBRG) Scheduling Algorithm for Input-Queued ATM Switches

Contact Info

Product

Resources

About