Proceedings of the ACM SIGCOMM 2019 Workshop on Networking for Emerging Applications and Technologies最新文献

Toward Consistent State Management of Adaptive Programmable Networks Based on P4 基于P4的自适应可编程网络一致性状态管理研究

Proceedings of the ACM SIGCOMM 2019 Workshop on Networking for Emerging Applications and Technologies Pub Date : 2019-08-14 DOI: 10.1145/3341558.3342202

Mu He, Andreas Blenk, W. Kellerer, S. Schmid

引用次数: 11

Network Support for Emerging Applications: Flexible Network Services as Frameworks? (Keynote) 新兴应用的网络支持:灵活的网络服务框架?(主题)

Proceedings of the ACM SIGCOMM 2019 Workshop on Networking for Emerging Applications and Technologies Pub Date : 2019-08-14 DOI: 10.1145/3341558.3359665

Zhi-Li Zhang

引用次数: 0

Efficient Dynamic Isolation of Congestion in Lossless DataCenter Networks 无损数据中心网络中拥塞的有效动态隔离

Proceedings of the ACM SIGCOMM 2019 Workshop on Networking for Emerging Applications and Technologies Pub Date : 2019-08-14 DOI: 10.1145/3341558.3342200

Luis Gonzalez-Naharro, J. Escudero-Sahuquillo, P. García, F. Quiles, J. Duato, Wenhao Sun, Ling Shen, Xiang Yu, Hewen Zheng

{"title":"Efficient Dynamic Isolation of Congestion in Lossless DataCenter Networks","authors":"Luis Gonzalez-Naharro, J. Escudero-Sahuquillo, P. García, F. Quiles, J. Duato, Wenhao Sun, Ling Shen, Xiang Yu, Hewen Zheng","doi":"10.1145/3341558.3342200","DOIUrl":"https://doi.org/10.1145/3341558.3342200","url":null,"abstract":"The architecture of modern DataCenters (DCs) has evolved to meet the stringent communication latency requirements of applications. RDMA technologies such as RoCEv2 have become mainstream to reduce latency, but their performance is impaired in systems with lossy networks due to the overload introduced by packet retransmissions. Thus, lossless networks are increasingly used in DCs to avoid retransmissions delays. However, lossless networks favor the occurrence of congestion, degrading network and system performance. Traditional congestion solutions, such as backpressure or injection throttling, may be ineffective when congestion arises from traffic generated by DC applications. Hence, new efficient congestion management strategies suited to the lossless networks of modern DCs are required. In this paper, we analyze congestion and its negative effects in these scenarios. In addition, we propose and evaluate a congestion management strategy that effectively eliminates the main negative effects of congestion, based on the dynamic isolation of congested flows in special queues. Unlike previous proposals based on this approach, a single special queue is shared by all the congested flows reaching a port. We also propose enhancements to this basic strategy to optimize its efficiency.","PeriodicalId":401123,"journal":{"name":"Proceedings of the ACM SIGCOMM 2019 Workshop on Networking for Emerging Applications and Technologies","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121270148","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 2

Deep Learning-based Short Video Recommendation and Prefetching for Mobile Commuting Users 基于深度学习的移动通勤用户短视频推荐与预取

Proceedings of the ACM SIGCOMM 2019 Workshop on Networking for Emerging Applications and Technologies Pub Date : 2019-08-14 DOI: 10.1145/3341558.3342205

Q. Li, Yuan Zhang, Hong Huang, Jinyao Yan

引用次数: 7

Dynamically Optimizing End-to-End Latency for Time-Triggered Networks 动态优化时间触发网络的端到端延迟

Proceedings of the ACM SIGCOMM 2019 Workshop on Networking for Emerging Applications and Technologies Pub Date : 2019-08-14 DOI: 10.1145/3341558.3342203

Zonghui Li, Hai Wan, Boxu Zhao, Yangdong Deng, M. Gu

{"title":"Dynamically Optimizing End-to-End Latency for Time-Triggered Networks","authors":"Zonghui Li, Hai Wan, Boxu Zhao, Yangdong Deng, M. Gu","doi":"10.1145/3341558.3342203","DOIUrl":"https://doi.org/10.1145/3341558.3342203","url":null,"abstract":"In time-triggered (TT) networks, frames for industrial control, so-called TT frames, are statically scheduled to be transmitted at precise sending points. Meanwhile, the remaining frames, so-called BE frames, are forwarded with best-effort (BE) strategies. TT frames meet application-specific end-to-end latency requirements by scheduling the worst cases. Furthermore, the planned sending points tend to prevent them from delivering as soon as possible. However, BE frames are transmitted as soon as possible but not assure bounded latency even lead to loss of frames due to queuing, congestion, etc. In this paper, we propose a BE assisted TT communication protocol (BEST TT protocol) to dynamically optimize end-to-end latency of TT frames by opportunistically taking advantage of BE transmission. Given a TT frame, the BEST TT protocol generates a cloned copy that is transmitted with the BE strategies. Whichever the TT frame or its copy, the first frame arriving at the end device is finally delivered and the other frame is ignored. So, the protocol ensures that the latency of the final delivered frame is not worse than that of the TT frame. We implement the protocol in an industry-strength TT switch and present three test scenarios to demonstrate its optimization compared with the previous state-of-art TT transmission.","PeriodicalId":401123,"journal":{"name":"Proceedings of the ACM SIGCOMM 2019 Workshop on Networking for Emerging Applications and Technologies","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115953619","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 3

Routing and Addressing with Length Variable IP Address 可变长度IP地址的路由和寻址

Proceedings of the ACM SIGCOMM 2019 Workshop on Networking for Emerging Applications and Technologies Pub Date : 2019-08-14 DOI: 10.1145/3341558.3342204

Shoushou Ren, Delei Yu, Guangpeng Li, Shihui Hu, Ye Tian, Xiangyang Gong, R. Moskowitz

{"title":"Routing and Addressing with Length Variable IP Address","authors":"Shoushou Ren, Delei Yu, Guangpeng Li, Shihui Hu, Ye Tian, Xiangyang Gong, R. Moskowitz","doi":"10.1145/3341558.3342204","DOIUrl":"https://doi.org/10.1145/3341558.3342204","url":null,"abstract":"IP addressing has become the core of Internet since the Internet was invented and its significance has never changed. However, with the dramatic development of Internet in recent years, the conventional IP address is facing with more and more problems, such as address exhaustion, low packet efficiency in Internet of Things, etc. The reason is that the conventional IP address is designed with fixed length, lacking of extensibility, while the demands for address varies greatly in different cases. To solve these problems, we propose a new address system called Flexible Address System (FAS). The FAS is designed with an infinite address space and can provide variable-length addresses on demand. Accordingly, multiple Routing Information Bases (RIBs) are used on routers to store FAS routing entries according to their different length. Further, a new data structure called Multi-Entrance-Trie (METrie) is proposed as the realization of multiple RIBs. The METrie is designed with multiple entrance nodes, enabling fast lookup. Experiments show that the METrie can achieve a high efficiency lookup on routers with less storage costs, implying that the FAS is friendly to the scale of routing table.","PeriodicalId":401123,"journal":{"name":"Proceedings of the ACM SIGCOMM 2019 Workshop on Networking for Emerging Applications and Technologies","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122460766","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 15

FlexNGIA FlexNGIA

Proceedings of the ACM SIGCOMM 2019 Workshop on Networking for Emerging Applications and Technologies Pub Date : 2019-08-14 DOI: 10.1145/3341558.3359666

M. Zhani

引用次数: 1

Analysis of Cellular Network Latency for Edge-Based Remote Rendering Streaming Applications 基于边缘的远程渲染流应用的蜂窝网络延迟分析

Proceedings of the ACM SIGCOMM 2019 Workshop on Networking for Emerging Applications and Technologies Pub Date : 2019-08-14 DOI: 10.1145/3341558.3342199

Zhehui Zhang, Shu Shi, Varun Gupta, R. Jana

引用次数: 8

A Framework for Qualitative Communications Using Big Packet Protocol 基于大分组协议的定性通信框架

Proceedings of the ACM SIGCOMM 2019 Workshop on Networking for Emerging Applications and Technologies Pub Date : 2019-06-25 DOI: 10.1145/3341558.3342201

Richard Li, K. Makhijani, Hamed Yousefi, C. Westphal, Lijun Dong, T. Wauters, F. Turck

{"title":"A Framework for Qualitative Communications Using Big Packet Protocol","authors":"Richard Li, K. Makhijani, Hamed Yousefi, C. Westphal, Lijun Dong, T. Wauters, F. Turck","doi":"10.1145/3341558.3342201","DOIUrl":"https://doi.org/10.1145/3341558.3342201","url":null,"abstract":"In the current Internet architecture, a packet is a minimal or fundamental unit upon which different actions such as classification, forwarding, or discarding are performed by the network nodes. When faced with constrained or poor network conditions, a packet is subjected to undesirable drops and re-transmissions, resulting in unpredictable delays and subsequent traffic overheads in the network. Alternately, we introduce qualitative communication services which allow partial, yet timely, delivery of a packet instead of dropping it entirely. These services allow breaking down packet payloads into smaller units (called chunks), enabling much finer granularity of bandwidth utilization. We propose Packet Wash as anew operation in forwarding nodes to support qualitative services. Upon packet error or network congestion, the forwarding node selectively removes some chunk(s) from the payload based on the relationship among the chunks or the individual signiicance level of each chunk. We also present a qualitative communication framework as well as a Packet Wash directive implemented in a newly evolved data plane technology, called Big Packet Protocol (BPP).","PeriodicalId":401123,"journal":{"name":"Proceedings of the ACM SIGCOMM 2019 Workshop on Networking for Emerging Applications and Technologies","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122639624","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 26

Proceedings of the ACM SIGCOMM 2019 Workshop on Networking for Emerging Applications and Technologies 2019年ACM SIGCOMM新兴应用与技术网络研讨会论文集

Proceedings of the ACM SIGCOMM 2019 Workshop on Networking for Emerging Applications and Technologies Pub Date : 1900-01-01 DOI: 10.1145/3341558

引用次数: 0