Framework for Data Center (DC) Network Virtualization

Balus, Florin; Morin, Thomas; Rekhter, Yakov; Bitar, Nabil; Lasserre, Marc

doi:10.17487/rfc7365

Cited by 24 publications

(20 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This document uses the same terminology as [RFC7365]. In addition, this document use the following terms.…”

Section: Terminologymentioning

confidence: 99%

“…This document uses the phrase "virtual network instance" with its ordinary meaning to represent an instance of a virtual network. Its usage may differ from the "VNI" acronym defined in the framework document [RFC7365]. The "VNI" acronym is not used in this document.…”

Section: Terminologymentioning

confidence: 99%

“…A third work area considers the attachment and detachment of VMs (or Tenant Systems [RFC7365], more generally) from a specific virtual network instance. When a VM attaches, the NVE associates the VM with a specific overlay for the purposes of tunneling traffic sourced from or destined to the VM.…”

Section: Control-plane Overlay Networking Work Areasmentioning

confidence: 99%

“…The data-plane encapsulation header carries a VN Context identifier [RFC7365] for the virtual network to which the data packet belongs. Numerous encapsulation or tunneling protocols already exist that can be leveraged.…”

Section: Data-plane Work Areasmentioning

confidence: 99%

See 3 more Smart Citations

Problem Statement: Overlays for Network Virtualization

Napierala¹,

Kreeger²,

Narten³

et al. 2014

View full text Add to dashboard Cite

show abstract

“…This document uses the same terminology as [RFC7365]. In addition, this document use the following terms.…”

Section: Terminologymentioning

confidence: 99%

Section: Terminologymentioning

confidence: 99%

Section: Control-plane Overlay Networking Work Areasmentioning

confidence: 99%

Section: Data-plane Work Areasmentioning

confidence: 99%

See 2 more Smart Citations

Problem Statement: Overlays for Network Virtualization

Napierala¹,

Kreeger²,

Narten³

et al. 2014

View full text Add to dashboard Cite

show abstract

“…A cutting-edge network virtualization is mainly based on two approaches, Hop-by-Hop and EdgeOverlay, however, the former requires a fully OpenFlow [2] ready network environment. The Edge-Overlay approach or Network Virtualization Overlays over Layer 3 (NVO3) [3] introduces L2-in-L3 tunneling between Tunnel End-Points (TEPs) to convey virtual traffic over physical networks. That is, the performance characteristic of the tunneling protocol can affect overall performance of virtual networks.…”

Section: Introductionmentioning

confidence: 99%

Accelerating the Performance of Software Tunneling Using a Receive Offload-Aware Novel L4 Protocol

Kawashima

Matsuo

2015

IEICE Trans. Commun.

View full text Add to dashboard Cite

Ryota KAWASHIMA †a) and Hiroshi MATSUO †b) , Members SUMMARY An L2-in-L3 tunneling technology plays an important role in network virtualization based on the concept of Software-Defined Networking (SDN). VXLAN (Virtual eXtensible LAN) and NVGRE (Network Virtualization using Generic Routing Encapsulation) protocols are being widely used in public cloud datacenters. These protocols resolve traditional VLAN problems such as a limitation of the number of virtual networks, however, their network performances are low without dedicated hardware acceleration. Although STT (Stateless Transport Tunneling) achieves far better performance, it has pragmatic problems in that STT packets can be dropped by network middleboxes like stateful firewalls because of modified TCP header semantics. In this paper, we propose yet another layer 4 protocol (Segment-oriented Connection-less Protocol, SCLP) for existing tunneling protocols. Our previous study revealed that the high-performance of STT mainly comes from 2-level software packet pre-reassembly before decapsulation. The SCLP header is designed to take advantage of such processing without modifying existing protocol semantics. We implement a VXLAN over SCLP tunneling and evaluate its performance by comparing with the original VXLAN (over UDP), NVGRE, Geneve, and STT. The results show that the throughput of the proposed method was comparable to STT and almost 70% higher than that of other protocols. key words: Software-Defined Networking, network virtualization, Network Function Virtualization, datacenter networks IntroductionMany functionalities of various network appliances including routers, switches, and firewalls have been migrated to virtual networks with the notion of Network Function Virtualization (NFV) [1]. A cutting-edge network virtualization is mainly based on two approaches, Hop-by-Hop and EdgeOverlay, however, the former requires a fully OpenFlow [2] ready network environment. The Edge-Overlay approach or Network Virtualization Overlays over Layer 3 (NVO3) [3] introduces L2-in-L3 tunneling between Tunnel End-Points (TEPs) to convey virtual traffic over physical networks. That is, the performance characteristic of the tunneling protocol can affect overall performance of virtual networks. In the NFV concept, high-performance ability of virtual networks is a key requirement for service quality. VXLAN has been adopted as RFC 7348 and supported by various platforms. However, VXLAN-based communications with software switches limit the performance of virtual networks compared with no-encapsulation communications [6], and the performance of NVGRE is almost the same with VXLAN. STT (Stateless Transport Tunneling) [7] had been proposed to achieve high-performance tunneling by exploiting a hardware offload feature of NIC (TCP Segmentation Offload [8], TSO). The STT protocol has a pseudo-TCP header to disguise STT packets as normal TCP packets as well as to make the STT protocol connection-less and stateless. The use of the pseudo-TCP header, however, causes an additional problem...

show abstract

Future Directions in Cable Networks, Services and Management

Toy¹

2015

Cable Networks, Services, and Management

View full text Add to dashboard Cite

Framework for Data Center (DC) Network Virtualization

Abstract: This document provides a framework for Data Center (DC) Network Virtualization over Layer 3 (NVO3) and defines a reference model along with logical components required to design a solution.

Cited by 24 publications

References 4 publications

Problem Statement: Overlays for Network Virtualization

Problem Statement: Overlays for Network Virtualization

Accelerating the Performance of Software Tunneling Using a Receive Offload-Aware Novel L4 Protocol

Future Directions in Cable Networks, Services and Management

Contact Info

Product

Resources

About