idnits 2.17.1 draft-xu-lsr-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 (October 18, 2018) is 2010 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) No issues found here. Summary: 1 error (**), 0 flaws (~~), 1 warning (==), 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 Alibaba Inc 4 Intended status: Standards Track L. Fang 5 Expires: April 21, 2019 Expedia, Inc 6 J. Tantsura 7 Apstra, Inc. 8 S. Ma 9 Juniper 10 October 18, 2018 12 OSPF Flooding Reduction in MSDC 13 draft-xu-lsr-ospf-flooding-reduction-in-msdc-01 15 Abstract 17 OSPF is commonly used as an underlay routing protocol for MSDC 18 (Massively Scalable Data Center) networks. For a given OSPF router 19 within the CLOS topology, it would receive multiple copies of exactly 20 the same LSA from multiple OSPF neighbors. In addition, two OSPF 21 neighbors may send each other the same LSA simultaneously. The 22 unneccessary link-state information flooding wastes the precious 23 process resource of OSPF routers greatly due to the fact that there 24 are too many OSPF neighbors for each OSPF router within the CLOS 25 topology. This document proposes some extensions to OSPF so as to 26 reduce the OSPF flooding within MSDC networks greatly. The reduction 27 of the OSPF flooding is much beneficial to improve the scalability of 28 MSDC networks. These modifications are applicable to both OSPFv2 and 29 OSPFv3. 31 Requirements Language 33 The key words "MUST", "MUST NOT", "REQUIRED", "SHALL", "SHALL NOT", 34 "SHOULD", "SHOULD NOT", "RECOMMENDED", "MAY", and "OPTIONAL" in this 35 document are to be interpreted as described in RFC 2119 [RFC2119]. 37 Status of This Memo 39 This Internet-Draft is submitted in full conformance with the 40 provisions of BCP 78 and BCP 79. 42 Internet-Drafts are working documents of the Internet Engineering 43 Task Force (IETF). Note that other groups may also distribute 44 working documents as Internet-Drafts. The list of current Internet- 45 Drafts is at https://datatracker.ietf.org/drafts/current/. 47 Internet-Drafts are draft documents valid for a maximum of six months 48 and may be updated, replaced, or obsoleted by other documents at any 49 time. It is inappropriate to use Internet-Drafts as reference 50 material or to cite them other than as "work in progress." 52 This Internet-Draft will expire on April 21, 2019. 54 Copyright Notice 56 Copyright (c) 2018 IETF Trust and the persons identified as the 57 document authors. All rights reserved. 59 This document is subject to BCP 78 and the IETF Trust's Legal 60 Provisions Relating to IETF Documents 61 (https://trustee.ietf.org/license-info) in effect on the date of 62 publication of this document. Please review these documents 63 carefully, as they describe your rights and restrictions with respect 64 to this document. Code Components extracted from this document must 65 include Simplified BSD License text as described in Section 4.e of 66 the Trust Legal Provisions and are provided without warranty as 67 described in the Simplified BSD License. 69 Table of Contents 71 1. Introduction . . . . . . . . . . . . . . . . . . . . . . . . 2 72 2. Terminology . . . . . . . . . . . . . . . . . . . . . . . . . 4 73 3. Modifications to Current OSPF Behaviors . . . . . . . . . . . 4 74 3.1. OSPF Routers as Non-DRs . . . . . . . . . . . . . . . . . 4 75 3.2. Controllers as DR/BDR . . . . . . . . . . . . . . . . . . 5 76 4. Acknowledgements . . . . . . . . . . . . . . . . . . . . . . 5 77 5. IANA Considerations . . . . . . . . . . . . . . . . . . . . . 5 78 6. Security Considerations . . . . . . . . . . . . . . . . . . . 6 79 7. References . . . . . . . . . . . . . . . . . . . . . . . . . 6 80 7.1. Normative References . . . . . . . . . . . . . . . . . . 6 81 7.2. Informative References . . . . . . . . . . . . . . . . . 6 82 Authors' Addresses . . . . . . . . . . . . . . . . . . . . . . . 6 84 1. Introduction 86 OSPF is commonly used as an underlay routing protocol for Massively 87 Scalable Data Center (MSDC) networks where CLOS is the most popular 88 toplogy. For a given OSPF router within the CLOS topology, it would 89 receive multiple copies of exactly the same LSA from multiple OSPF 90 neighbors. In addition, two OSPF neighbors may send each other the 91 same LSA simultaneously. The unnecessary link-state information 92 flooding wastes the precious process resource of OSPF routers greatly 93 and therefore OSPF could not scale very well in MSDC networks. 95 To simplify the network management task, centralized controllers are 96 becoming fundamental network elements in most MSDCs. One or more 97 controllers are usually connected to all routers within the MSDC 98 network via a Local Area Network (LAN) which is dedicated for network 99 management purpose (called management LAN), as shown in Figure 1. 101 +----------+ +----------+ 102 |Controller| |Controller| 103 +----+-----+ +-----+----+ 104 |DR |BDR 105 | | 106 | | 107 ---+---------+---+----------+-----------+---+---------+-Management LAN 108 | | | | | 109 |Non-DR |Non-DR |Non-DR |Non-DR |Non-DR 110 | | | | | 111 | +---+--+ | +---+--+ | 112 | |Router| | |Router| | 113 | *------*- | /*---/--* | 114 | / \ -- | // / \ | 115 | / \ -- | // / \ | 116 | / \ --|// / \ | 117 | / \ /*- / \ | 118 | / \ // | -- / \ | 119 | / \ // | -- / \ | 120 | / /X | -- \ | 121 | / // \ | / -- \ | 122 | / // \ | / -- \ | 123 | / // \ | / -- \ | 124 | / // \ | / -- \ | 125 | / // \ | / -- \ | 126 | / // \ | / -- \ | 127 +-+- //* +\\+-/-+ +---\-++ 128 |Router| |Router| |Router| 129 +------+ +------+ +------+ 131 Figure 1 133 With the assistance of controllers acting as OSPF Designated Router 134 (DR)/Backup Designated Router (BDR) for the management LAN, OSPF 135 routers within the MSDC network don't need to exchange any other 136 types of OSPF packet than the OSPF Hello packet among them. As 137 specified in [RFC2328], these Hello packets are used for the purpose 138 of establishing and maintaining neighbor relationships and ensuring 139 bidirectional communication between OSPF neighbors, and even the DR/ 140 BDR election purpose in the case where those OSPF routers are 141 connected to a broadcast network. In order to obtain the full 142 topology information (i.e., the fully synchronized link-state 143 database) of the MSDC's network, these OSPF routers just need to 144 exchange the link-state information with the controllers being 145 elected as OSPF DR/BDR for the management LAN instead. 147 To further suppress the flooding of multicast OSPF packets originated 148 from OSPF routers over the management LAN, OSPF routers would not 149 send multicast OSPF Hello packets over the management LAN. Insteads, 150 they just wait for OSPF Hello packets originated from the controllers 151 being elected as OSPF DR/BDR initially. Once OSPF DR/BDR for the 152 management LAN have been discovered, they start to send OSPF Hello 153 packets directly (as unicasts) to OSPF DR/BDR periodically. In 154 addition, OSPF routers would send other types of OSPF packets (e.g., 155 Database Descriptor packet, Link State Request packet, Link State 156 Update packet, Link State Acknowledgment packet) to OSPF DR/BDR for 157 the management LAN as unicasts as well. In contrast, the controllers 158 being elected as OSPF DR/BDR would send OSPF packets as specified in 159 [RFC2328]. As a result, OSPF routers would not receive OSPF packets 160 from one another unless these OSPF packets are forwarded as unknown 161 unicasts over the management LAN. Through the above modifications to 162 the current OSPF router behaviors, the OSPF flooding is greatly 163 reduced, which is much beneficial to improve the scalability of MSDC 164 networks. These modifications are applicable to both OSPFv2 165 [RFC2328] and OSPFv3 [RFC5340]. 167 Furthermore, the mechanism for OSPF refresh and flooding reduction in 168 stable topologies as described in [RFC4136] could be considered as 169 well. 171 2. Terminology 173 This memo makes use of the terms defined in [RFC2328]. 175 3. Modifications to Current OSPF Behaviors 177 3.1. OSPF Routers as Non-DRs 179 After the exchange of OSPF Hello packets among OSPF routers, the OSPF 180 neighbor relationship among them would transition to and remain in 181 the TWO-WAY state. OSPF routers would originate Router-LSAs and/or 182 Network-LSAs accordingly depending upon the link-types. Note that 183 the neighbors in the TWO-WAY state would be advertised in the Router- 184 LSAs and/or Network-LSA. This is a little bit different from the 185 OSPF router behavior as specified in [RFC2328] where the neighbors in 186 the TWO-WAY state would not be advertised. However, these self- 187 originated LSAs need not to be exchanged directly among them anymore. 188 Instead, these LSAs just need to be sent solely to the controllers 189 being elected as OSPF DR/BDR for the management LAN. 191 To further reduce the flood of multicast OSPF packets over the 192 management LAN, OSPF routers SHOULD send OSPF packets as unicasts. 193 More specifically, OSPF routers SHOULD send unicast OSPF Hello 194 packets periodically to the controllers being elected as OSPF DR/BDR. 195 In other words, OSPF routers would not send any OSPF Hello packet 196 over the management LAN until they have found OSPF DR/BDR for the 197 management LAN. Note that OSPF routers SHOULD NOT be elected as OSPF 198 DR/BDR for the management LAN (This is done by setting the Router 199 Priority of those OSPF routers to zero). As a result, OSPF routers 200 would not see each other over the management LAN. Furthermore, OSPF 201 routers SHOULD send all other types of OSPF packets than OSPF Hello 202 packets (i.e., Database Descriptor packet, Link State Request packet, 203 Link State Update packet, Link State Acknowledgment packet) to the 204 controllers being elected as OSPF DR/BDR as unicasts as well. 206 To avoid the data traffic from being forwarded across the management 207 LAN, the cost of all OSPF routers' interfaces to the management LAN 208 SHOULD be set to the maximum value. 210 When a given OSPF router lost its connection to the management LAN, 211 it SHOULD actively establish FULL adjacency with all of its OSPF 212 neighbors within the CLOS network. As such, it could obtain the full 213 LSDB of the CLOS network while flooding its self-originated LSAs to 214 the remaining part of the whole network. That's to say, for a given 215 OSPF router within the CLOS network, it would not actively establish 216 FULL adjacency with its OSPF neighbor in the TWO-WAY state by 217 default. However, it SHOULD NOT refuse to establish FULL adjacency 218 with a given OSPF neighbors when receiving Database Description 219 Packets from that OSPF neighbor. 221 3.2. Controllers as DR/BDR 223 The controllers being elected as OSPF DR/BDR would send OSPF packets 224 as multicasts or unicasts as per [RFC2328]. In addition, Link State 225 Acknowledgment packets are RECOMMENDED to be sent as unicasts rather 226 than multicasts if possible. 228 4. Acknowledgements 230 The authors would like to thank Acee Lindem for his valuable comments 231 and suggestions on this document. 233 5. IANA Considerations 235 TBD. 237 6. Security Considerations 239 TBD. 241 7. References 243 7.1. Normative References 245 [RFC2119] Bradner, S., "Key words for use in RFCs to Indicate 246 Requirement Levels", BCP 14, RFC 2119, 247 DOI 10.17487/RFC2119, March 1997, 248 . 250 [RFC2328] Moy, J., "OSPF Version 2", STD 54, RFC 2328, 251 DOI 10.17487/RFC2328, April 1998, 252 . 254 [RFC5340] Coltun, R., Ferguson, D., Moy, J., and A. Lindem, "OSPF 255 for IPv6", RFC 5340, DOI 10.17487/RFC5340, July 2008, 256 . 258 7.2. Informative References 260 [RFC4136] Pillay-Esnault, P., "OSPF Refresh and Flooding Reduction 261 in Stable Topologies", RFC 4136, DOI 10.17487/RFC4136, 262 July 2005, . 264 Authors' Addresses 266 Xiaohu Xu 267 Alibaba Inc 269 Email: xiaohu.xxh@alibaba-inc.com 271 Luyuan Fang 272 Expedia, Inc 274 Email: luyuanf@gmail.com 276 Jeff Tantsura 277 Apstra, Inc. 279 Email: jefftant.ietf@gmail.com 280 Shaowen Ma 281 Juniper 283 Email: mashao@juniper.net