idnits 2.17.1 draft-xu-ospf-flooding-reduction-in-msdc-01.txt: Checking boilerplate required by RFC 5378 and the IETF Trust (see https://trustee.ietf.org/license-info): ---------------------------------------------------------------------------- No issues found here. Checking nits according to https://www.ietf.org/id-info/1id-guidelines.txt: ---------------------------------------------------------------------------- No issues found here. Checking nits according to https://www.ietf.org/id-info/checklist : ---------------------------------------------------------------------------- ** There is 1 instance of too long lines in the document, the longest one being 1 character in excess of 72. Miscellaneous warnings: ---------------------------------------------------------------------------- == The copyright year in the IETF Trust and authors Copyright Line does not match the current year -- The document date (May 4, 2017) is 2549 days in the past. Is this intentional? -- Found something which looks like a code comment -- if you have code sections in the document, please surround them with '' and '' lines. Checking references for intended status: Proposed Standard ---------------------------------------------------------------------------- (See RFCs 3967 and 4897 for information about using normative references to lower-maturity documents in RFCs) == Unused Reference: 'RFC5838' is defined on line 263, but no explicit reference was found in the text Summary: 1 error (**), 0 flaws (~~), 2 warnings (==), 2 comments (--). Run idnits with the --verbose option for more detailed information about the items above. -------------------------------------------------------------------------------- 2 Network Working Group X. Xu 3 Internet-Draft Huawei 4 Intended status: Standards Track L. Fang 5 Expires: November 5, 2017 ebay 6 J. Tantsura 7 Individual 8 May 4, 2017 10 OSPF Flooding Reduction in MSDC 11 draft-xu-ospf-flooding-reduction-in-msdc-01 13 Abstract 15 OSPF is commonly used as an underlay routing protocol for MSDC 16 (Massively Scalable Data Center) networks. For a given OSPF router 17 within the CLOS topology, it would receive multiple copies of exactly 18 the same LSA from multiple OSPF neighbors. In addition, two OSPF 19 neighbors may send each other the same LSA simultaneously. The 20 unneccessary link-state information flooding wastes the precious 21 process resource of OSPF routers greatly due to the fact that there 22 are too many OSPF neighbors for each OSPF router within the CLOS 23 topology. This document proposes some extensions to OSPF so as to 24 reduce the OSPF flooding within MSDC networks greatly. The reduction 25 of the OSPF flooding is much beneficial to improve the scalability of 26 MSDC networks. These modifications are applicable to both OSPFv2 and 27 OSPFv3. 29 Status of This Memo 31 This Internet-Draft is submitted in full conformance with the 32 provisions of BCP 78 and BCP 79. 34 Internet-Drafts are working documents of the Internet Engineering 35 Task Force (IETF). Note that other groups may also distribute 36 working documents as Internet-Drafts. The list of current Internet- 37 Drafts is at http://datatracker.ietf.org/drafts/current/. 39 Internet-Drafts are draft documents valid for a maximum of six months 40 and may be updated, replaced, or obsoleted by other documents at any 41 time. It is inappropriate to use Internet-Drafts as reference 42 material or to cite them other than as "work in progress." 44 This Internet-Draft will expire on November 5, 2017. 46 Copyright Notice 48 Copyright (c) 2017 IETF Trust and the persons identified as the 49 document authors. All rights reserved. 51 This document is subject to BCP 78 and the IETF Trust's Legal 52 Provisions Relating to IETF Documents 53 (http://trustee.ietf.org/license-info) in effect on the date of 54 publication of this document. Please review these documents 55 carefully, as they describe your rights and restrictions with respect 56 to this document. Code Components extracted from this document must 57 include Simplified BSD License text as described in Section 4.e of 58 the Trust Legal Provisions and are provided without warranty as 59 described in the Simplified BSD License. 61 Table of Contents 63 1. Introduction . . . . . . . . . . . . . . . . . . . . . . . . 2 64 1.1. Requirements Language . . . . . . . . . . . . . . . . . . 4 65 2. Terminology . . . . . . . . . . . . . . . . . . . . . . . . . 4 66 3. Modifications to Current OSPF Behaviors . . . . . . . . . . . 4 67 3.1. OSPF Routers as Non-DRs . . . . . . . . . . . . . . . . . 4 68 3.2. Controllers as DR/BDR . . . . . . . . . . . . . . . . . . 5 69 4. Acknowledgements . . . . . . . . . . . . . . . . . . . . . . 5 70 5. IANA Considerations . . . . . . . . . . . . . . . . . . . . . 5 71 6. Security Considerations . . . . . . . . . . . . . . . . . . . 6 72 7. References . . . . . . . . . . . . . . . . . . . . . . . . . 6 73 7.1. Normative References . . . . . . . . . . . . . . . . . . 6 74 7.2. Informative References . . . . . . . . . . . . . . . . . 6 75 Authors' Addresses . . . . . . . . . . . . . . . . . . . . . . . 6 77 1. Introduction 79 OSPF is commonly used as an underlay routing protocol for Massively 80 Scalable Data Center (MSDC) networks where CLOS is the most popular 81 toplogy. For a given OSPF router within the CLOS topology, it would 82 receive multiple copies of exactly the same LSA from multiple OSPF 83 neighbors. In addition, two OSPF neighbors may send each other the 84 same LSA simultaneously. The unnecessary link-state information 85 flooding wastes the precious process resource of OSPF routers greatly 86 and therefore OSPF could not scale very well in MSDC networks. 88 To simplify the network management task, centralized controllers are 89 becoming fundamental network elements in most MSDCs. One or more 90 controllers are usually connected to all routers within the MSDC 91 network via a Local Area Network (LAN) which is dedicated for network 92 management purpose (called management LAN), as shown in Figure 1. 94 +----------+ +----------+ 95 |Controller| |Controller| 96 +----+-----+ +-----+----+ 97 |DR |BDR 98 | | 99 | | 100 ---+---------+---+----------+-----------+---+---------+-Management LAN 101 | | | | | 102 |Non-DR |Non-DR |Non-DR |Non-DR |Non-DR 103 | | | | | 104 | +---+--+ | +---+--+ | 105 | |Router| | |Router| | 106 | *------*- | /*---/--* | 107 | / \ -- | // / \ | 108 | / \ -- | // / \ | 109 | / \ --|// / \ | 110 | / \ /*- / \ | 111 | / \ // | -- / \ | 112 | / \ // | -- / \ | 113 | / /X | -- \ | 114 | / // \ | / -- \ | 115 | / // \ | / -- \ | 116 | / // \ | / -- \ | 117 | / // \ | / -- \ | 118 | / // \ | / -- \ | 119 | / // \ | / -- \ | 120 +-+- //* +\\+-/-+ +---\-++ 121 |Router| |Router| |Router| 122 +------+ +------+ +------+ 124 Figure 1 126 With the assistance of controllers acting as OSPF Designated Router 127 (DR)/Backup Designated Router (BDR) for the management LAN, OSPF 128 routers within the MSDC network don't need to exchange any other 129 types of OSPF packet than the OSPF Hello packet among them. As 130 specified in [RFC2328], these Hello packets are used for the purpose 131 of establishing and maintaining neighbor relationships and ensuring 132 bidirectional communication between OSPF neighbors, and even the DR/ 133 BDR election purpose in the case where those OSPF routers are 134 connected to a broadcast network. In order to obtain the full 135 topology information (i.e., the fully synchronized link-state 136 database) of the MSDC's network, these OSPF routers just need to 137 exchange the link-state information with the controllers being 138 elected as OSPF DR/BDR for the management LAN instead. 140 To further suppress the flooding of multicast OSPF packets originated 141 from OSPF routers over the management LAN, OSPF routers would not 142 send multicast OSPF Hello packets over the management LAN. Insteads, 143 they just wait for OSPF Hello packets originated from the controllers 144 being elected as OSPF DR/BDR initially. Once OSPF DR/BDR for the 145 management LAN have been discovered, they start to send OSPF Hello 146 packets directly (as unicasts) to OSPF DR/BDR periodically. In 147 addition, OSPF routers would send other types of OSPF packets (e.g., 148 Database Descriptor packet, Link State Request packet, Link State 149 Update packet, Link State Acknowledgment packet) to OSPF DR/BDR for 150 the management LAN as unicasts as well. In contrast, the controllers 151 being elected as OSPF DR/BDR would send OSPF packets as specified in 152 [RFC2328]. As a result, OSPF routers would not receive OSPF packets 153 from one another unless these OSPF packets are forwarded as unknown 154 unicasts over the management LAN. Through the above modifications to 155 the current OSPF router behaviors, the OSPF flooding is greatly 156 reduced, which is much beneficial to improve the scalability of MSDC 157 networks. These modifications are applicable to both OSPFv2 158 [RFC2328] and OSPFv3 [RFC5340]. 160 Furthermore, the mechanism for OSPF refresh and flooding reduction in 161 stable topologies as described in [RFC4136] could be considered as 162 well. 164 1.1. Requirements Language 166 The key words "MUST", "MUST NOT", "REQUIRED", "SHALL", "SHALL NOT", 167 "SHOULD", "SHOULD NOT", "RECOMMENDED", "MAY", and "OPTIONAL" in this 168 document are to be interpreted as described in RFC 2119 [RFC2119]. 170 2. Terminology 172 This memo makes use of the terms defined in [RFC2328]. 174 3. Modifications to Current OSPF Behaviors 176 3.1. OSPF Routers as Non-DRs 178 After the exchange of OSPF Hello packets among OSPF routers, the OSPF 179 neighbor relationship among them would transition to and remain in 180 the TWO-WAY state. OSPF routers would originate Router-LSAs and/or 181 Network-LSAs accordingly depending upon the link-types. Note that 182 the neighbors in the TWO-WAY state would be advertised in the Router- 183 LSAs and/or Network-LSA. This is a little bit different from the 184 OSPF router behavior as specified in [RFC2328] where the neighbors in 185 the TWO-WAY state would not be advertised. However, these self- 186 originated LSAs need not to be exchanged directly among them anymore. 187 Instead, these LSAs just need to be sent solely to the controllers 188 being elected as OSPF DR/BDR for the management LAN. 190 To further reduce the flood of multicast OSPF packets over the 191 management LAN, OSPF routers SHOULD send OSPF packets as unicasts. 192 More specifically, OSPF routers SHOULD send unicast OSPF Hello 193 packets periodically to the controllers being elected as OSPF DR/BDR. 194 In other words, OSPF routers would not send any OSPF Hello packet 195 over the management LAN until they have found OSPF DR/BDR for the 196 management LAN. Note that OSPF routers SHOULD NOT be elected as OSPF 197 DR/BDR for the management LAN (This is done by setting the Router 198 Priority of those OSPF routers to zero). As a result, OSPF routers 199 would not see each other over the management LAN. Furthermore, OSPF 200 routers SHOULD send all other types of OSPF packets than OSPF Hello 201 packets (i.e., Database Descriptor packet, Link State Request packet, 202 Link State Update packet, Link State Acknowledgment packet) to the 203 controllers being elected as OSPF DR/BDR as unicasts as well. 205 To avoid the data traffic from being forwarded across the management 206 LAN, the cost of all OSPF routers' interfaces to the management LAN 207 SHOULD be set to the maximum value. 209 When a given OSPF router lost its connection to the management LAN, 210 it SHOULD actively establish FULL adjacency with all of its OSPF 211 neighbors within the CLOS network. As such, it could obtain the full 212 LSDB of the CLOS network while flooding its self-originated LSAs to 213 the remaining part of the whole network. That's to say, for a given 214 OSPF router within the CLOS network, it would not actively establish 215 FULL adjacency with its OSPF neighbor in the TWO-WAY state by 216 default. However, it SHOULD NOT refuse to establish FULL adjacency 217 with a given OSPF neighbors when receiving Database Description 218 Packets from that OSPF neighbor. 220 3.2. Controllers as DR/BDR 222 The controllers being elected as OSPF DR/BDR would send OSPF packets 223 as multicasts or unicasts as per [RFC2328]. In addition, Link State 224 Acknowledgment packets are RECOMMENDED to be sent as unicasts rather 225 than multicasts if possible. 227 4. Acknowledgements 229 The authors would like to thank Acee Lindem for his valuable comments 230 and suggestions on this document. 232 5. IANA Considerations 234 TBD. 236 6. Security Considerations 238 TBD. 240 7. References 242 7.1. Normative References 244 [RFC2119] Bradner, S., "Key words for use in RFCs to Indicate 245 Requirement Levels", BCP 14, RFC 2119, 246 DOI 10.17487/RFC2119, March 1997, 247 . 249 [RFC2328] Moy, J., "OSPF Version 2", STD 54, RFC 2328, 250 DOI 10.17487/RFC2328, April 1998, 251 . 253 [RFC5340] Coltun, R., Ferguson, D., Moy, J., and A. Lindem, "OSPF 254 for IPv6", RFC 5340, DOI 10.17487/RFC5340, July 2008, 255 . 257 7.2. Informative References 259 [RFC4136] Pillay-Esnault, P., "OSPF Refresh and Flooding Reduction 260 in Stable Topologies", RFC 4136, DOI 10.17487/RFC4136, 261 July 2005, . 263 [RFC5838] Lindem, A., Ed., Mirtorabi, S., Roy, A., Barnes, M., and 264 R. Aggarwal, "Support of Address Families in OSPFv3", 265 RFC 5838, DOI 10.17487/RFC5838, April 2010, 266 . 268 Authors' Addresses 270 Xiaohu Xu 271 Huawei 273 Email: xuxiaohu@huawei.com 275 Luyuan Fang 276 ebay 278 Email: lufang@ebay.com 279 Jeff Tantsura 280 Individual 282 Email: jefftant@gmail.com