NetCloud 2013 Non-Tunneling Edge-Overlay Model using OpenFlow for Cloud Datacenter Networks Nagoya Institute of Technology, Japan Ryota Kawashima and Hiroshi.

Slides:



Advertisements
Similar presentations
Virtual Machine Queue Architecture Review Ali Dabagh Architect Windows Core Networking Don Stanwyck Sr. Program Manager NDIS Virtualization.
Advertisements

Copyright © 2004 Juniper Networks, Inc. Proprietary and Confidentialwww.juniper.net 1 E-VPN and Data Center R. Aggarwal
Internetworking II: MPLS, Security, and Traffic Engineering
Connect communicate collaborate GN3plus What the network should do for clouds? Christos Argyropoulos National Technical University of Athens (NTUA) Institute.
Copyright © 2014, Oracle and/or its affiliates. All rights reserved. | Oracle’s Next-Generation SDN Platform Andrew Thomas Architect Corporate Architecture.
DOT – Distributed OpenFlow Testbed
Network Virtualization Overlay Control Protocol Requirements draft-kreeger-nvo3-overlay-cp-00 Lawrence Kreeger, Dinesh Dutt, Thomas Narten, David Black,
Computer Networks20-1 Chapter 20. Network Layer: Internet Protocol 20.1 Internetworking 20.2 IPv IPv6.
Introduction into VXLAN Russian IPv6 day June 6 th, 2012 Frank Laforsch Systems Engineer, EMEA
OpenFlow overview Joint Techs Baton Rouge. Classic Ethernet Originally a true broadcast medium Each end-system network interface card (NIC) received every.
NCCA 2014 Performance Evaluation of Non-Tunneling Edge-Overlay Model on 40GbE Environment Nagoya Institute of Technology, Japan Ryota Kawashima and Hiroshi.
PARIS: ProActive Routing In Scalable Data Centers Dushyant Arora, Theophilus Benson, Jennifer Rexford Princeton University.
Switching Topic 4 Inter-VLAN routing. Agenda Routing process Routing VLANs – Traditional model – Router-on-a-stick – Multilayer switches EtherChannel.
Intel ® Ethernet Depths of the Cloud: How Linux Networking needs to evolve Peter (PJ) Waskiewicz Shannon Nelson.
Outlines Backgrounds Goals Implementation Performance Evaluation
Improving performance of overlay-based virtual networks
Scalable and Crash-Tolerant Load Balancing based on Switch Migration
Internetworking Introduction How Networks Differ How Networks Can Be Connected Concatenated Virtual Circuits Connectionless Internetworking Tunneling Fragmentation.
VLANs (Virtual LANs) CS 158B Elaine Lim Allison Nham.
NVO3 Requirements for Tunneling Igor Gashinsky and Bruce Davie IETF.
Microsoft Virtual Academy Module 4 Creating and Configuring Virtual Machine Networks.
MPLS And The Data Center Adrian Farrel Old Dog Consulting / Juniper Networks
Authors: Vic Liu, Chen Li China Mobile Speaker: Vic Liu China Mobile NaaS (Network as a service) Requirement draft-liu-nvo3-naas-requirement-00.
Virtual LANs. VLAN introduction VLANs logically segment switched networks based on the functions, project teams, or applications of the organization regardless.
Data Center Network Redesign using SDN
The Network Layer. Network Projects Must utilize sockets programming –Client and Server –Any platform Please submit one page proposal Can work individually.
IEEE 802.1q - VLANs Nick Poorman.
Virtualization Infrastructure Administration Network Jakub Yaghob.
Generic Network Virtualization Encapsulation draft-gross-geneve-00 Pankaj Garg Jesse Gross
© 2006 Cisco Systems, Inc. All rights reserved.Cisco PublicITE I Chapter 6 1 Connecting to the Network Networking for Home and Small Businesses – Chapter.
Draft-bitar-nvo3-vpn-applicability-00.txt Page - 1 Cloud Networking: Framework and VPN Applicability draft-bitar-nvo3-vpn-applicability-00.txt Nabil Bitar.
© 2007 Cisco Systems, Inc. All rights reserved.Cisco Public ITE PC v4.0 Chapter 1 1 Connecting to the Network Networking for Home and Small Businesses.
Semester 3—LAN Switching Chapter 2 Objectives  By the end of this chapter we will be able to perform tasks related to: – Various LAN Communication Problems.
1 © OneCloud and/or its affiliates. All rights reserved. VXLAN Overview Module 4.
Stateless Transport Tunneling draft-davie-stt-01.txt Bruce Davie, Jesse Gross, Igor Gashinsky et al.
1 © 2003, Cisco Systems, Inc. All rights reserved. CCNA 3 v3.0 Module 9 Virtual Trunking Protocol.
L2TP-VP: Layer Two Tunneling Protocol - Virtualization Profile draft-fan-l2tp-vp-00 Duoliang Fan, Liang Xia, Zhen Cao, Namgon Kim November 2013 Vancouver.
SOFTWARE DEFINED NETWORKING/OPENFLOW: A PATH TO PROGRAMMABLE NETWORKS April 23, 2012 © Brocade Communications Systems, Inc.
1 VLANs Relates to Lab 6. Short module on basics of VLAN switching.
The Goals Proposal Realizing broadcast/multicast in virtual networks
VXLAN Nexus 9000 Essentials for the Data Center Karim Afifi
Switch 1 Switch 2 Switch 3 Blocking Forwarding ROOT BRIDGE BRIDGE’S ROOT PORT DESIGNATED PORT DESIGNATED BRIDGE.
Ethernet Virtual LANs Hubs versus Switches –Hubs broadcast bits out all ports –Switches usually send a frame out a one port More fundamentally –In unicasting,
VSE: Virtual Switch Extension for Adaptive CPU Core Assignment in softirq Shin Muramatsu, Ryota Kawashima Shoichi Saito, Hiroshi Matsuo Nagoya Institute.
1 Copyright © 2009 Juniper Networks, Inc. E-VPN for NVO Use of Ethernet Virtual Private Network (E-VPN) as the carrier-grade control plane.
March th IETF - Prague1 TRILL Working Group Changes from draft-trill-rbridge-protocol-02.txt to draft-trill-rbridge-protocol-03.txt Dinesh Dutt,
November 2006IETF TRILL WG1 TRILL Working Group draft-gai-perlman-trill-encap-00.txt as modified by Radia Ed Bowen, IBM Dinesh Dutt, Cisco Silvano Gai,
Understanding “Virtual” Networks J.J. Ekstrom Fall 2011.
T3: TCP-based High-Performance and Congestion-aware Tunneling Protocol for Cloud Networking Satoshi Ogawa† Kazuki Yamazaki† Ryota Kawashima† Hiroshi Matsuo†
EVPN: Or how I learned to stop worrying and love the BGP
@projectcalico Sponsored by Simple, Secure, Scalable networking for the virtualized datacentre UKNOF 33 Ed 19 th January 2016.
AVS Brazos : IPv6. Agenda AVS IPv6 background Packet flows TSO/TCO Configuration Demo Troubleshooting tips Appendix.
Network Processing Systems Design
Considerations for Benchmarking Virtual Networks Samuel Kommu, Jacob Rapp, Ben Basler,
Network Virtualization Ben Pfaff Nicira Networks, Inc.
EVPN: Or how I learned to stop worrying and love the BGP Tom Dwyer, JNCIE-ENT #424 Clay Haynes, JNCIE-SEC # 69 JNCIE-ENT # 492.
Determining Topology from a Capture File
Heitor Moraes, Marcos Vieira, Italo Cunha, Dorgival Guedes
Need for high performance Data Plane
TRILL MPLS-Based Ethernet VPN
The good, the bad and the ugly…
Ethernet : Framing and Addressing
Network base Network base.
NTHU CS5421 Cloud Computing
EVPN a very short introduction
Connecting to the Network
NetCloud Hong Kong 2017/12/11 NetCloud Hong Kong 2017/12/11 PA-Flow:
IS-IS VPLS for Data Center Network draft-xu-l2vpn-vpls-isis-02
MICROSOFT NETWORK VIRTUALIZATION
Chapter 4: outline 4.1 Overview of Network layer data plane
Presentation transcript:

NetCloud 2013 Non-Tunneling Edge-Overlay Model using OpenFlow for Cloud Datacenter Networks Nagoya Institute of Technology, Japan Ryota Kawashima and Hiroshi Matsuo

Outlines Backgrounds Edge-Overlay (Distributed Tunnels) Proposed method Evaluation Conclusion 2

Backgrounds – Network Virtualization Multi-tenant Datacenter Networks  Each tenant uses virtual networks  Each virtual network shares the physical network resources Physical network /8 VM Virtual network /24 Virtual network /16 Virtual network /8 Tenant 1 Tenant 2 Tenant 3 3

Backgrounds – VLAN limitations Each virtual network has its own VLAN ID A VLAN tag is inserted into Ethernet frames Ethernet VLAN PayloadFCS Problems with VLAN The maximum number of VLANs is 4094 Physical switches learn VMs' MAC addresses VLAN ID (1 ~ 4094) is included 4 VM's frame

Backgrounds – Edge-Overlay L2-in-L3 tunneling VM Virtual switch Physical server VLAN problems can be addressed Over 16 million virtual networks can be supported VMs' MAC addresses are hidden from physical switches Existing network devices can be used Virtual switches provide many high-level functions 5 Virtual switch

Tunneling protocols Ethernet (Physical) IP (Physical) VXLAN UDP FCS Ethernet (Virtual) Payload VXLAN VM's frame Ethernet (Physical) IP (Physical) NVGRE FCS Ethernet (Virtual) Payload NVGRE VM's frame Ethernet (Physical) IP (Physical) STT TCP-like FCS Ethernet (Virtual) Payload STT VM's frame 24bit ID 64bit ID TCP-like header NIC offloading (TSO) 6

Problems with Tunneling (1 / 2) IP Fragmentation at the physical server Payload Header Payload Header Payload Header VM Physical Server HeaderPayload Header Fragmentation 7

Problems with Tunneling (2 / 2) Compatibility with existing environment  IP Multicasting should be supported (VXLAN)  Load balancing (ECMP) is not supported (NVGRE)  Firewalls, IDS, load balancer may discard the frames (STT)  TSO cannot be used (VXLAN, NVGRE) Practical problem  Supported protocols differs between products (vendor lock-in) 8

Proposed Method Yet another edge-overlay method  Tunneling protocols are not used  No IP fragmentation at the physical server layer  OpenFlow-enabled virtual switches  No VLAN limitations  Compatibility with existing environment 9

Method1 - MAC Address Translation MAC addresses within the frame are replaced  SRC address : VM1's address => SV1's address  DEST address : VM2's address => SV2's address VM 1 VM 2 VM1 => VM2 Physical Server (SV1)Physical Server (SV2) SV1 => SV2 SV1 => VM2 VMs' MAC addresses are hidden from the physical switches Virtual Switch 10

Method2 – Host-based VLAN VM Tenant 1Tenant 2 VID=10 VID=20 Server VM Tenant 1 Tenant 2 VID=20 VID=10 Virtual Network (VID10) Virtual Network (VID20) Traditional VM Tenant 1Tenant 2 VID=10 VID=20 VID=30 Server VM Tenant 1 Tenant 2 VID=20 VID=10 Proposal VID is globally unique VID is unique within a server 11

Feature Comparison 12 ProposalVXLANNVGRESTTVLAN Physical NetworkL2L2 / L3 L2 MAC address hiding ✔✔✔✔ - No. of virtual networksUnlimited16 million 18 quintillion4094 IP Multicasting-Required--- Load balancing (ECMP) ✔✔ - ✔✔ FW, IDS, LB Transparency ✔✔✔ - ✔ IP Fragmentation (Physical) -Occur - TSO support ✔ -- ✔✔

Performance Evaluation VM-to-VM communication 13 Virtual switch Physical server 1 VM1 (Sender) Iperf client VM2 (Receiver) Physical server 2 GbE switching hub Virtual switch OpenFlow Controller Iperf server GRE / VXLAN tunnel

Evaluation Result (UDP) The performance of proposed method was equal to "Optimal" IP fragmentation affected the no. of frames and performance Fragmentation at the VM Fragmentation by GRE encapsulation Fragmentation by VXLAN encapsulation The no. of frames = 3 The no. of frames = 5 14

Conclusion Yet another Edge-overlay method  No tunneling protocols  No IP fragmentation at physical server layer  Higher throughput than tunneling protocols  L2 network Future Work  Further evaluation is necessary 10/40 GbE environment  MPLS support 15