检索结果-内蒙古大学图书馆

DCI-NACC: flow scheduling and congestion control based on programmable data plane in high-performance data center networks

引用

INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY 2022年第1期122卷 51-63页

作者： Geng, Junjie Commun Univ China State Key Lab Media Convergence & Commun Beijing Peoples R China

PFC (Priority-based Flow Control), which is used to give full play to the performance advantages of RDMA, can cause problems such as head-of-line (HoL) blocking. PFC-based method cannot eliminate the congestion fundamentally. At the same time, another approach to deal with congestion in the data center networks, commonly known as "injection throttling" mechanism, may result in slower effective response due to the delay between congestion detection and feedback to the sources. In this article, we have optimized the two types of algorithms (DCI and NACC) and used them in combination (DCI-NACC). We propose a novel scheduling strategy of combining PFC-based algorithm and "injection throttling"-based algorithm using programmable data plane device for lossless data center networks. Specifically, we design a dynamic congestion isolation (DCI) method to optimize PFC. DCI ensures lossless transmission in the data center networks and eliminates the HoL blocking problem caused by PFC. We also propose a network-assisted congestion control (NACC) algorithm in which the feedback information is directly sent from the switch where congestion occurs in the network. NACC increases the efficiency of network congestion perception and reduces the delay that feedback take effect. Experimental results show that, compared with PFC and ECN algorithm, DCI-NACC algorithm has significant improvement in network performance (normalized throughput, network latency, and flow completion time). Especially, simulation experiments show that NACC can greatly reduce the number of times that PFC PAUSE is triggered. The simulation experiments confirm that DCI-NACC algorithm can effectively improve the performance of the data center networks on the basis of lossless transmission.

关键词： Congestion control Lossless transmission programmable data plane Traffic scheduling High-performance data centers

来源：评论

学校读者我要写书评

暂无评论

Named data network dynamic cache placement strategy based on programmable data plane

引用

IET NETWORKS 2023年第1期12卷 27-35页

作者： Hou, Saifeng Hu, Yuxiang Tian, Le Informat Engn Univ Informat Technol Res Inst Zhengzhou Peoples R China

Aiming at the efficiency and implementation of in-network cache in Named data Network, an in-network cache method based on the programmable data plane was proposed. Set the cache port on the programmable data plane, when the cache policy determined that the content needs to be cached, set the output port as the cache port and forward it to the cache unit for caching According to the different requirements of different contents on Quality of Service, the request contents were classified. And the cache probability of classified contents was calculated based on the content popularity and the cache cooperation information between nodes. The cache threshold was dynamically set according to the state of cache space occupancy and compared with the cache probability to determine whether to cache the contents. Experimental results show that the proposed cache placement strategy can effectively improve the cache hit ratio and reduce the average transmission latency compared with the traditional cache placement strategy.

关键词： in-network cache method request contents cache probability Computer networks and techniques cache port cache unit content popularity cache policy cache space occupancy data network dynamic cache placement strategy programmable data plane classified contents cache threshold Computer communications cache cooperation information cache storage probability File organisation

来源：评论

学校读者我要写书评

暂无评论

vFFR: A Very Fast Failure Recovery Strategy Implemented in Devices With programmable data plane

IEEE OPEN JOURNAL OF THE COMMUNICATIONS SOCIETY

引用

IEEE OPEN JOURNAL OF THE COMMUNICATIONS SOCIETY 2024年 5卷 7121-7146页

作者： Franco, David Higuero, Marivi Sanz, Ane Unzilla, Juanjo Huarte, Maider Univ Basque Country UPV EHU Dept Commun Engn Bilbao 48013 Spain

The rapid emergence of new applications and services, and their increased demand for Quality of Service (QoS), have a significant impact on the development of today's communication networks. As a result, communication networks are constantly evolving towards new architectures, such as the 6th Generation (6G) of communication systems, currently being studied in academic and research environments. One of the most critical aspects of designing communication networks is meeting the restricted delay and packet loss requirements. In this context, although link failure recovery has been widely addressed in the literature, it remains one of the main causes of packet losses and delays in the network. The failure recovery time in currently deployed technologies is still far from the sub-millisecond delay required in 6G networks. The time required for distributed network architectures to converge to a common network state after a link failure is excessive. In contrast, centralized architectures such as Software-Defined Networking (SDN) solve this problem but still need to notify the failure to a centralized controller, which increases the recovery time. This paper proposes a very Fast Failure Recovery (vFFR) strategy that can recover from link failures in sub-millisecond timescales by reacting directly from the data plane of the network devices while maintaining a synchronized state with the centralized controller. We first analyze current failure recovery strategies and classify them according to the techniques used to optimize failure recovery time. Afterward, we describe the design of a vFFR strategy that combines three data plane recovery algorithms to reduce latency and packet loss under varying network conditions. Our vFFR strategy has been modeled in P4 language and tested on an emulation platform to validate the three data plane recovery algorithms under different conditions. The results show that latency varies according to the alternate path selected in the recovery

关键词： Delays Quality of service Packet loss 6G mobile communication Emulation Communication networks Reviews Process control Computer architecture Technological innovation Link failure failure recovery programmable data plane P4 SDN 6G

来源：评论

学校读者我要写书评

暂无评论

Virtualization in programmable data plane: A Survey and Open Challenges

IEEE OPEN JOURNAL OF THE COMMUNICATIONS SOCIETY

引用

IEEE OPEN JOURNAL OF THE COMMUNICATIONS SOCIETY 2020年 1卷 527-534页

作者： Han, Sol Jang, Seokwon Choi, Hongrok Lee, Hochan Pack, Sangheon Korea Univ Sch Elect Engn Seoul 02841 South Korea

programmable data plane (PDP) is an emerging technology for programming packet processing tasks by means of a domain-specific high-level language (e.g., programming protocol-independent packet processor (P4)) and programmable switch chips. Recently, several PDP virtualization schemes have been introduced to enable more flexible and elastic network management. In this article, we first give an overview PDP and P4. After that, existing PDP virtualization schemes are classified into hypervisorand compiler-based approaches and their pros and cons are analyzed in detail. Finally, open challenges for PDP virtualization are identified and future research directions are presented.

关键词： programmable data plane P4 virtualization

来源：评论

学校读者我要写书评

暂无评论

Flexible sampling-based in-band network telemetry in programmable data plane

引用

ICT EXPRESS 2020年第1期6卷 62-65页

作者： Suh, Dongeun Jang, Seokwon Han, Sol Pack, Sangheon Wang, Xiaofei Samsung Res Samsung Elect Seoul South Korea Korea Univ Sch Elect Engn Seoul South Korea Tianjin Univ Tianjin Key Lab Adv Networking Tianjin Peoples R China

In-band network telemetry (INT) is an emerging network monitoring framework based on a protocol-independent packet processor (P4). Network devices can be programmed with a domain-specific language to embed switch-internal states into data packets as they traverse through networks. However, the current P4-based INT does not support a sampling;thus, INT headers should be augmented for all incoming packets, which will incur high overhead in a large-scale network. In this paper, we propose a flexible sampling-based INT (FS-INT) scheme to address the aforementioned issues. Simulation results show that FS-INT can reduce the protocol overhead in a controlled manner while providing sufficiently high accuracy. (C) 2020 The Korean Institute of Communications and Information Sciences (KICS). Publishing services by Elsevier B.V.

关键词： programmable data plane In-band network telemetry Flexible sampling-based INT

来源：评论

学校读者我要写书评

暂无评论

HyperVDP: High-Performance Virtualization of the programmable data plane

引用

IEEE JOURNAL ON SELECTED AREAS IN COMMUNICATIONS 2019年第3期37卷 556-569页

作者： Zhang, Cheng Bi, Jun Zhou, Yu Wu, Jianping Tsinghua Univ Inst Network Sci & Cyberspace Beijing 100084 Peoples R China Tsinghua Univ Dept Comp Sci Beijing 100084 Peoples R China Beijing Natl Res Ctr Informat Sci & Technol Beijing 100084 Peoples R China CERNET Network Ctr Beijing 100084 Peoples R China

With the advent of P4-specific programmable data plane (PDP), network functions (NFs) can be offloaded into the PDP to achieve high performance guaranteed by hardware. Meanwhile, CPU powers consumed by NFs can be released to user applications. However, as more and more NFs can be offloaded, several problems rooted inside the PDP severely hinder it from facilitating this offloading trend. 1) The existing PDP provides the exclusive data plane abstraction where different NFs cannot operate the same data plane. 2) The PDP is hardly able to deploy NFs in a "hitless" manner. In this paper, we propose HyperVDP as a high-performance data plane hypervisor to provision non-exclusive abstraction and uninterrupted reconfigurability on the P4-specific PDP. To achieve virtualization, we design several innovative techniques to equally express functions of all programmable elements in the P4-specific PDP. We implement the prototype of HyperVDP on different target platforms, and evaluate different target-based prototypes by comparing with their counterparts. Results show that BMv2-target HyperVDP averagely prevails over its counterpart 2.5x in performance and 4x in resource efficiency. DPDK-target HyperVDP performs comparably to its counterparts while offering virtualization features which neither of its counterparts could provide.

关键词： Software defined networking network function virtualization programmable data plane p4

来源：评论

学校读者我要写书评

暂无评论

programmable data plane Applications in 5G and Beyond Architectures: A Systematic Review

引用

SENSORS 2023年第15期23卷 6955页

作者： Brito, Jorge Andres Moreno, Jose Ignacio Contreras, Luis Miguel Alvarez-Campana, Manuel Caamano, Marta Blanco Univ Politecn Madrid Dept Ingn Sistemas Telematicos ETSI Telecomunicac Madrid 28040 Spain Tel ID Madrid 28010 Spain

The rapid evolution of 5G and beyond technologies has sparked an unprecedented surge in the need for networking infrastructure that can deliver high speed, minimal latency, and remarkable flexibility. The programmable data plane, which enables the dynamic reconfiguration of network functions and protocols, is becoming increasingly important in meeting these requirements. This paper provides an overview of the current state of the art in programmable data planes implemented in 5G and beyond architectures. It proposes a classification of the reviewed studies based on system architecture and specific use cases. Furthermore, the article surveys the primary applications of programmable devices in emerging telecommunication networks, such as tunneling and forwarding, network slicing, cybersecurity, and in-band telemetry. Finally, this publication summarizes the open research challenges and future directions. In addition to offering a comprehensive review of programmable data plane applications in telecommunication networks, this article aims to guide further research in this promising field for network operators and researchers alike.

关键词： programmable data plane 5G and beyond architectures programmable devices P4 SDN

来源：评论

学校读者我要写书评

暂无评论

Port Knocking Implementation on programmable data plane 13

Port Knocking Implementation on Programmable Data Plane

引用

13th International Conference on Information and Communication Technology and System (ICTS)

作者： Nugroho, Muhammad Arief Prabowo, Sidik Saputra, Masud Adhi Abdurohman, Maman Telkom Univ Sch Comp Bandung Indonesia Telkom Univ SEE Minist Ind B4T Bandung Indonesia

ISBN: (纸本)9781665440592

This paper proposes the port knocking method to offload the network functions on Software-Defined Networks to programmable data plane. The main drawback of centralized SDN controller architecture is causing bottlenecks in the network because every packet that arrives at the switch must be forwarded to the controller first. The controller will decide whether the packet is allowed to be forwarded or dropped, resulting in increased processing delay for packet processing. There are several previous methods have been proposed. However, they could not meet the need of network performance. Thus, we decide to migrate the several controller functions in the data plane. This paper presents port knocking (PkoCK) implementation in programmable data plane. PKock successfully offloads the port knocking implementation to the data plane and reduces the processing delay 19% compared to SDN-based port knocking.

关键词： Port knocking programmable data plane SDN PKoCK

来源：评论

学校读者我要写书评

暂无评论

Machine-learning-assisted Traffic Classification of User Activities at programmable data plane 23

Machine-learning-assisted Traffic Classification of User Act...

引用

23rd Asia-Pacific Network Operations and Management Symposium (APNOMS)

作者： Zhu, Xinyu Zhang, Yue East China Normal Univ Minist Educ Engn Res Ctr Software Hardware Codesign Technol & Shanghai Peoples R China Beijing Univ Posts & Telecommun State Key Lab Networking & Switching Technol Beijing Peoples R China East China Normal Univ Natl Trusted Embedded Software Engn Technol Res C Shanghai Peoples R China

ISBN: (数字)9784885523397

ISBN: (纸本)9784885523397

The increasing diversity of network terminals not only brings the exponential growth of network traffic, but also increases the complexity of user activities analysis. Packet encryption and dynamic port techniques also bring new challenges to traffic classification. Machine Learning (ML) techniques have been deployed at the control plane of programmable networks with better accuracy and expensive communication overhead. This paper proposes a traffic classification framework with ML classifier offloaded to the programmable data plane to decrease communication overhead. Considering the limitation of memory space in programmable switches, we design a storage algorithm combining hash tables and Count-Min sketch to store traffic features to be used in the ML classifier. We first use K-Means to classify flows into different categories, then we use decision tree to obtain the activity labels. Experimental results show that the proposed traffic classification framework can achieve high classification accuracy (above 93.7%) with minor performance degradation.

关键词： Traffic Classification programmable Networks programmable data plane Machine Learning

来源：评论

学校读者我要写书评

暂无评论

iLoad: In-network Load Balancing with programmable data plane 15

iLoad: In-network Load Balancing with Programmable Data Plan...

引用

15th ACM International Conference on Emerging Networking EXperiments and Technologies (CoNEXT)

作者： Grigoryan, Garegin Liu, Yaoqing Kwon, Minseok Rochester Inst Technol Rochester NY 14623 USA Fairleigh Dickinson Univ Teaneck NJ USA

ISBN: (纸本)9781450370066

Several cloud service and data center providers have announced plans to transition towards environmental-friendly green computing. From a computer networking perspective, such transition requires novel routing approaches over traditional networking protocols, more specifically, end-host-driven load balancing. For example, an end-host may issue a request to change its load, based on its current CPU load or energy availability. Our solution, iLoad, collects such requests from end-hosts and computes the routes entirely in the data plane, providing more efficient and reliable operation of a network.

关键词： Load balancing Green computing programmable data plane

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：