Throughput Evaluation of Kernel based Packet Switching in a Multi-core System

Vladislavic, Dani; Topic, Gregori; Huljenić, Darko; Vrgoc, Katarina Andela; Ožegović, Julije

doi:10.23919/softcom.2019.8903740

Cited by 3 publications

(8 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our model, on the other hand, has the ambition to be applied for these kinds of architectures. Our previous work [2] presented throughput evaluation methodology based on execution area (EA) distribution derived from general packet processing steps in kernel packet switching. We analyzed throughput results at different points in the system in relation to EA distribution by core pinning, which is considered as CPU resource consumption modeling parameter for the optimal throughput in different scenarios where virtual switching is applied.…”

Section: Related Workmentioning

confidence: 99%

“…The previous work [2] introduced the methodology of performance evaluation of packet processing systems based on execution areas (EAs). This methodology is further used as a baseline for throughput prediction model construction.…”

Section: Execution Area-based Throughput Prediction Modelingmentioning

confidence: 99%

“…Three CPU-exhausting EAs are extracted based on the presented EA criteria. 10 Gbps NIC in testbed processes packets on a line speed rate regardless of frame size so it cannot bottleneck the system throughput [2].…”

Section: Software Execution Areas Of the Representative Nf/vnfmentioning

confidence: 99%

“…Following related researches, the model defined in the study presumes CPU processing capacity to be the bottleneck in packet processing systems. The model arises from the novel methodology of throughput evaluation based on execution area (EA) distribution derived from general packet processing steps in operating system kernel defined in our previous work [2]. This study extends the work in [2] to consider processing in VMs.…”

Section: Introductionmentioning

confidence: 97%

“…The model arises from the novel methodology of throughput evaluation based on execution area (EA) distribution derived from general packet processing steps in operating system kernel defined in our previous work [2]. This study extends the work in [2] to consider processing in VMs. The proposed methodology, in accordance with empirical EA bottleneck determination, is used to build a set of optimal modeling system configurations for the target VNF and NFVI architectures per given number of CPU core resources.…”

Section: Introductionmentioning

confidence: 97%

See 4 more Smart Citations

Virtual Network Resource Optimization Model for Network Function Virtualization

Vladislavic

Huljenić

Ožegović

2021

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

Network function virtualization (NFV) is a concept aimed at achieving telecom grade cloud ecosystem for new-generation networks focusing on capital and operational expenditure (CAPEX and OPEX) savings. This study introduces empirical throughput prediction model for the virtual network function (VNF) and network function virtualization infrastructure (NFVI) architectures based on Linux kernel. The model arises from the methodology for performance evaluation and modeling based on execution area (EA) distribution by CPU core pinning. EA is defined as a software execution unit that can run isolated on a compute resource (CPU core). EAs are derived from the elements and packet processing principles in NFVIs and VNFs based on Linux kernel. Performing measurements and observing linearity of the measured results open the possibility to apply model calibration technique to achieve general VNF and NFVI architecture model with performance prediction and environment setup optimization. The modeling parameters are derived from the cumulative packet processing cost obtained by measurements for collocated EAs on the CPU core hosting the bottleneck EA. The VNF and NFVI architecture model with performance prediction is successfully validated against the measurement results obtained in emulated environment and used to predict optimal system configurations and maximal throughput results for different CPUs.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Execution Area-based Throughput Prediction Modelingmentioning

confidence: 99%

Section: Software Execution Areas Of the Representative Nf/vnfmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 97%

Section: Introductionmentioning

confidence: 97%

See 3 more Smart Citations

Virtual Network Resource Optimization Model for Network Function Virtualization

Vladislavic

Huljenić

Ožegović

2021

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

show abstract

SRPerf: A Performance Evaluation Framework for IPv6 Segment Routing

Abdelsalam

Ventre

Scarpitta

et al. 2021

IEEE Trans. Netw. Serv. Manage.

View full text Add to dashboard Cite

SRPerf: a Performance Evaluation Framework for IPv6 Segment Routing

Abdelsalam¹,

Ventre²,

Scarpitta³

et al. 2020

Preprint

View full text Add to dashboard Cite

Segment Routing is a form of loose source routing. It provides the ability to include a list of instructions (called segments), in the packet headers. The Segment Routing architecture has been first implemented with the MPLS dataplane and then, quite recently, with the IPv6 dataplane (SRv6). IPv6 Segment Routing (SRv6) is a promising solution to support advanced services such as Traffic Engineering, Service Function Chaining, Virtual Private Networks, and Load Balancing. The SRv6 data-plane is supported in many different software forwarding engines including the Linux kernel and VPP software router, as well as in hardware devices. In this paper, we present SRPerf, a performance evaluation framework for software and hardware implementations of SRv6. SRPerf is able to perform different benchmarking tests such as throughput and latency. For throughput tests, we use the Partial Drop Rate (PDR) to characterize a system under test. The architecture of SRPerf can be easily extended to support new benchmarking methodologies as well as different SRv6 implementations. We have used SRPerf to evaluate the performance of the SRv6 implementation in the Linux kernel and in VPP. SRPerf is a valuable tool in the context of software forwarding engines where new features can be added at fast pace, as it helps experimenters to validate their work. In particular, we describe how we have leveraged SRPerf to validate the implementation of some SRv6 behaviors that were missing or wrongly implemented in the Linux kernel mainline.

show abstract

Throughput Evaluation of Kernel based Packet Switching in a Multi-core System

Cited by 3 publications

References 14 publications

Virtual Network Resource Optimization Model for Network Function Virtualization

Virtual Network Resource Optimization Model for Network Function Virtualization

SRPerf: A Performance Evaluation Framework for IPv6 Segment Routing

SRPerf: a Performance Evaluation Framework for IPv6 Segment Routing

Contact Info

Product

Resources

About