idnits 2.17.1 draft-allman-tcp-sack-00.txt: Checking boilerplate required by RFC 5378 and the IETF Trust (see https://trustee.ietf.org/license-info): ---------------------------------------------------------------------------- ** Looks like you're using RFC 2026 boilerplate. This must be updated to follow RFC 3978/3979, as updated by RFC 4748. Checking nits according to https://www.ietf.org/id-info/1id-guidelines.txt: ---------------------------------------------------------------------------- ** The document seems to lack a 1id_guidelines paragraph about 6 months document validity -- however, there's a paragraph with a matching beginning. Boilerplate error? == No 'Intended status' indicated for this document; assuming Proposed Standard Checking nits according to https://www.ietf.org/id-info/checklist : ---------------------------------------------------------------------------- ** The document seems to lack an IANA Considerations section. (See Section 2.2 of https://www.ietf.org/id-info/checklist for how to handle the case when there are no actions for IANA.) ** The document seems to lack separate sections for Informative/Normative References. All references will be assumed normative when checking for downward references. ** There is 1 instance of lines with control characters in the document. ** The document seems to lack a both a reference to RFC 2119 and the recommended RFC 2119 boilerplate, even if it appears to use RFC 2119 keywords. RFC 2119 keyword, line 91: '...d in this document the scoreboard MUST...' RFC 2119 keyword, line 99: '... and therefore SACKed data MUST NOT be...' RFC 2119 keyword, line 105: '...s sent, the scoreboard MUST be updated...' RFC 2119 keyword, line 113: '... This routine MUST return the seque...' RFC 2119 keyword, line 116: '... routine MUST return the sequen...' (16 more instances...) Miscellaneous warnings: ---------------------------------------------------------------------------- -- The document seems to lack a disclaimer for pre-RFC5378 work, but may have content which was first submitted before 10 November 2008. If you have contacted all the original authors and they are all willing to grant the BCP78 rights to the IETF Trust, then this is fine, and you can ignore this comment. If not, you may need to add the pre-RFC5378 disclaimer. (See the Legal Provisions document at https://trustee.ietf.org/license-info for more information.) -- Couldn't find a document date in the document -- date freshness check skipped. Checking references for intended status: Proposed Standard ---------------------------------------------------------------------------- (See RFCs 3967 and 4897 for information about using normative references to lower-maturity documents in RFCs) == Missing Reference: 'RFC2018' is mentioned on line 56, but not defined -- Possible downref: Non-RFC (?) normative reference: ref. 'AHKO97' -- Possible downref: Non-RFC (?) normative reference: ref. 'All00' -- Possible downref: Non-RFC (?) normative reference: ref. 'FF96' -- Possible downref: Non-RFC (?) normative reference: ref. 'Jac90' -- Possible downref: Non-RFC (?) normative reference: ref. 'PF00' ** Obsolete normative reference: RFC 793 (Obsoleted by RFC 9293) ** Obsolete normative reference: RFC 2581 (Obsoleted by RFC 5681) ** Obsolete normative reference: RFC 2582 (Obsoleted by RFC 3782) Summary: 9 errors (**), 0 flaws (~~), 2 warnings (==), 7 comments (--). Run idnits with the --verbose option for more detailed information about the items above. -------------------------------------------------------------------------------- 1 Internet Engineering Task Force Mark Allman 2 INTERNET DRAFT NASA GRC/BBN 3 File: draft-allman-tcp-sack-00.txt Ethan Blanton 4 Ohio University 5 November, 2000 6 Expires: May, 2001 8 A Conservative SACK-based Loss Recovery Algorithm for TCP 10 Status of this Memo 12 This document is an Internet-Draft and is in full conformance with 13 all provisions of Section 10 of RFC2026. 15 Internet-Drafts are working documents of the Internet Engineering 16 Task Force (IETF), its areas, and its working groups. Note that 17 other groups may also distribute working documents as 18 Internet-Drafts. 20 Internet-Drafts are draft documents valid for a maximum of six 21 months and may be updated, replaced, or obsoleted by other documents 22 at any time. It is inappropriate to use Internet- Drafts as 23 reference material or to cite them other than as "work in progress." 25 The list of current Internet-Drafts can be accessed at 26 http://www.ietf.org/ietf/1id-abstracts.txt 28 The list of Internet-Draft Shadow Directories can be accessed at 29 http://www.ietf.org/shadow.html. 31 Abstract 33 This document presents a conservative loss recovery algorithm for 34 TCP that is based on the use of the selective acknowledgment TCP 35 option. The algorithm presented in this document conforms to the 36 spirit of the current congestion control specification, but allows 37 TCP senders to recover more effectively when multiple segments are 38 lost from a single flight of data. 40 1 Introduction 42 This document presents a conservative loss recovery algorithm for 43 TCP that is based on the use of the selective acknowledgment TCP 44 option. While the TCP selective acknowledgment (SACK) option 45 [RFC2018] is being steadily deployed in the Internet [All00] there 46 is evidence that hosts are not using the SACK information when 47 making retransmission and congestion control decisions [PF00]. The 48 goal of this document is to outline one straightforward method for 49 TCP implementations to use SACK information to increase performance. 51 [RFC2581] allows advanced loss recovery algorithms to be used by TCP 52 [RFC793] provided that they follow the spirit of TCP's congestion 53 control algorithms [RFC2581,RFC2914]. [RFC2582] outlines one such 54 advanced recovery algorithm called NewReno. This document outlines 55 a loss recovery algorithm that uses the selective acknowledgment 56 (SACK) [RFC2018] TCP option to enhance TCP's loss recovery. The 57 algorithm outlined in this document, heavily based on the algorithm 58 detailed in [FF96], is a conservative replacement of the fast 59 recovery algorithm [Jac90,RFC2581]. The algorithm specified in this 60 document is a straightforward SACK-based loss recovery strategy that 61 follows the guidelines set in [RFC2581] and can safely be used in 62 TCP implementations. Alternate SACK-based loss recovery methods can 63 be used in TCP as implementers see fit (as long as the alternate 64 algorithms follow the guidelines provided in [RFC2581]). 66 2 Definitions 68 The reader is expected to be familiar with the definitions given in 69 [RFC2581]. 71 For the purposes of explaining the SACK-based loss recovery 72 algorithm we define two variables that a TCP sender stores: 74 ``HighACK'' is the sequence number of the highest cumulative ACK 75 received at a given point. 77 ``HighData'' is the highest sequence number transmitted at a 78 given point. 80 For the purposes of this specification we define a ``duplicate 81 acknowledgment'' as an acknowledgment (ACK) whose cumulative ACK 82 number is equal to the current value of HighACK and also conveys new 83 selective acknowledgment information for segment(s) above HighACK. 85 3 Keeping Track of SACK Information 87 For a TCP sender to implement the algorithm defined in the next 88 section it must keep a data structure to store incoming selective 89 acknowledgment information on a per connection basis. Such a data 90 structure is commonly called the ``scoreboard''. For the purposes 91 of the algorithm defined in this document the scoreboard MUST 92 implement the following functions: 94 Update (): 96 Each octet that is cumulatively ACKed or SACKed should be marked 97 accordingly in the scoreboard data structure, and the total 98 number of octets SACKed should be recorded. Note that SACK 99 information is advisory and therefore SACKed data MUST NOT be 100 removed from TCP's retransmission buffer until the data is 101 cumulatively acknowledged. 103 MarkRetran (): 105 When a retransmission is sent, the scoreboard MUST be updated 106 with this information so that data is not repeatedly 107 retransmitted by the SACK-based algorithm outlined in this 108 document. Note: If a retransmission is lost it will be repaired 109 using TCP's retransmission timer. 111 NextSeg (): 113 This routine MUST return the sequence number range of the oldest 114 segment that has not been cumulatively ACKed or SACKed and not 115 been retransmitted. If no such segment is available this 116 routine MUST return the sequence number range for the first 117 previously unsent segment (if such a segment exists). 119 AmountSACKed (): 121 This routine MUST return the number of octets selectively 122 acknowledged by the receiver. 124 LeftNetwork (): 126 This function MUST return the number of octets in the given 127 sequence number range that have left the network. The algorithm 128 checks each octet in the given range and separately keeps track 129 of the number of retransmitted octets and the number of octets 130 that are cumulatively ACKed but were not SACKed. Note: it is 131 possible to have octets that fit both categories. In this case, 132 the octets MUST be counted in both categories. After checking 133 the sequence number range given this routine returns the sum of 134 the two counters. 136 Note: The SACK-based loss recovery algorithm outlined in this 137 document requires more computational resources than previous TCP 138 loss recovery strategies. However, we believe the scoreboard data 139 structure can be implemented in a reasonably efficient manner (both 140 in terms of computation complexity and memory usage) in most TCP 141 implementations. 143 4 Algorithm Details 145 Upon the receipt of the first and second duplicate ACKs, the 146 scoreboard MUST be updated per the selective acknowledgment 147 information contained in the ACK (via the Update () routine). Note: 148 The first and second duplicate ACKs can also be used to trigger the 149 transmission of previously unsent segments using the Limited 150 Transmit mechanism [ABF00]. 152 When a TCP sender receives the third duplicate ACK the scoreboard 153 MUST be updated with the new SACK information (via Update ()) and a 154 loss recovery phase SHOULD be initiated, per the fast retransmit 155 algorithm outlined in [RFC2581], and the following steps MUST be 156 taken: 158 (1) Set a ``pipe'' variable to the number of outstanding octets 159 (i.e., octets that have been sent but not yet acknowledged), per 160 the following equation: 162 pipe = HighData - HighACK - AmountSACKed () 163 (2) Set a ``RecoveryPoint'' variable to HighData. When the TCP 164 sender receives a cumulative ACK for this data octet the loss 165 recovery phase is terminated. 167 (3) The congestion window (cwnd) is reduced to half its current 168 value. The value of the slow start threshold (ssthresh) is set 169 to the halved value of cwnd. 171 (4) Retransmit the first data segment not covered by HighACK. Use 172 the MarkRetran () function to mark the sequence number range as 173 having been retransmitted in the scoreboard. 175 Once a TCP is in the loss recovery phase the following procedure 176 MUST be used for each arriving ACK: 178 (A) An incoming cumulative ACK for a sequence number greater than or 179 equal to RecoveryPoint signals the end of loss recovery and the 180 loss recovery phase MUST be terminated. 182 (B) Upon receipt of a duplicate ACK the following actions MUST be 183 taken: 185 (B.1) Use Update () to record the new SACK information conveyed 186 by the incoming ACK. 188 (B.2) The pipe variable is decremented by the number of newly 189 SACKed data octets conveyed in the incoming ACK, as that is 190 the amount of new data that has left the network. 192 (C) When a ``partial ACK'' (an ACK that increases the HighACK point, 193 but does not terminate loss recovery) arrives, the following 194 actions MUST be performed: 196 (C.1) Before updating HighACK based on the received cumulative 197 ACK, save HighACK as OldHighACK. 199 (C.2) The scoreboard MUST be updated based on the cumulative ACK 200 and any new SACK information that is included in the ACK via 201 the Update () routine. 203 (C.3) The value of pipe MUST be decremented by the number of 204 octets returned by the LeftNetwork () routine when given the 205 sequence number range OldHighACK-HighACK. 207 (D) If pipe is less than cwnd and the receiver's advertised window 208 permits, the TCP sender SHOULD transmit a segment, as follows: 210 (D.1) The scoreboard MUST be queried via NextSeg () for the 211 sequence number range of the next segment to transmit, and 212 the given segment is sent. 214 (D.2) The pipe variable MUST be incremented by the number of 215 data octets sent in (D.1). 217 5 Research 219 The algorithm specified in this document is analyzed in [FF96], 220 which shows that the above algorithm is effective in reducing 221 transfer time over standard TCP Reno [RFC2581] when multiple 222 segments are dropped from a window of data (especially as the number 223 of drops increases). [AHKO97] shows that the algorithm defined in 224 this document can greatly improve throughput in connections 225 traversing satellite channels. 227 6 Security Considerations 229 The algorithm presented in this paper shares security considerations 230 with [RFC2581]. A key difference is that an algorithm based on 231 SACKs is more robust against attackers forging duplicate ACKs to 232 force the TCP sender to reduce cwnd. With SACKs TCP senders have an 233 additional check on whether the ACK is legitimate or not. While not 234 fool-proof, SACK provides some amount of protection in this area. 236 Acknowledgments 238 The authors wish to thank Sally Floyd for encouraging this document 239 and commenting on an early draft. The algorithm described in this 240 document is largely based on an algorithm outlined by Kevin Fall and 241 Sally Floyd in [FF96] (although the authors of this document assume 242 responsibility for any mistakes in the above). We thank Vern Paxson 243 for providing valuable feedback on an early version of this draft. 244 Finally, we thank Matt Mathis and Jamshid Mahdavi for implementing 245 the scoreboard in ns and hence guiding our thinking in keeping track 246 of SACK state. 248 References 250 [ABF00] Mark Allman, Hari Balakrishnan, Sally Floyd. Enhancing 251 TCP's Loss Recovery Using Limited Transmit, August 252 2000. Internet-Draft draft-ietf-tsvwg-limited-xmit-00.txt (work 253 in progress). 255 [AHKO97] Mark Allman, Chris Hayes, Hans Kruse, Shawn Ostermann. TCP 256 Performance Over Satellite Links. Proceedings of the Fifth 257 International Conference on Telecommunications Systems, 258 Nashville, TN, March, 1997. 260 [All00] Mark Allman. A Web Server's View of the Transport Layer. ACM 261 Computer Communication Review, 30(5), October 2000. 263 [FF96] Kevin Fall and Sally Floyd. Simulation-based Comparisons of 264 Tahoe, Reno and SACK TCP. Computer Communication Review, July 265 1996. 267 [Jac90] Van Jacobson. Modified TCP Congestion Avoidance Algorithm. 268 Technical Report, LBL, April 1990. 270 [PF00] Jitendra Padhye, Sally Floyd. TBIT, the TCP Behavior 271 Inference Tool, October 2000. http://www.aciri.org/tbit/. 273 [RFC793] Jon Postel, Transmission Control Protocol, STD 7, RFC 793, 274 September 1981. 276 [RFC2581] Mark Allman, Vern Paxson, W. Richard Stevens, TCP 277 Congestion Control, RFC 2581, April 1999. 279 [RFC2582] Sally Floyd and Tom Henderson. The NewReno Modification 280 to TCP's Fast Recovery Algorithm, RFC 2582, April 1999. 282 [RFC2914] Sally Floyd. Congestion Control Principles, RFC 2914, 283 September 2000. 285 Author's Addresses: 287 Mark Allman 288 NASA Glenn Research Center/BBN Technologies 289 Lewis Field 290 21000 Brookpark Rd. MS 54-2 291 Cleveland, OH 44135 292 Phone: 216-433-6586 293 Fax: 216-433-8705 294 mallman@grc.nasa.gov 295 http://roland.grc.nasa.gov/~mallman 297 Ethan Blanton 298 Ohio University Internetworking Research Lab 299 Stocker Center 300 Athens, OH 45701 301 eblanton@cs.ohiou.edu