idnits 2.17.1 draft-ietf-bmwg-b2b-frame-02.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 : ---------------------------------------------------------------------------- -- The draft header indicates that this document updates RFC2544, but the abstract doesn't seem to directly say this. It does mention RFC2544 though, so this could be OK. Miscellaneous warnings: ---------------------------------------------------------------------------- == The copyright year in the IETF Trust and authors Copyright Line does not match the current year == The document seems to lack the recommended RFC 2119 boilerplate, even if it appears to use RFC 2119 keywords -- however, there's a paragraph with a matching beginning. Boilerplate error? (The document does seem to have the reference to RFC 2119 which the ID-Checklist requires). (Using the creation date from RFC2544, updated by this document, for RFC5378 checks: 1999-03-01) -- 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.) -- The document date (May 19, 2020) is 1438 days in the past. Is this intentional? Checking references for intended status: Informational ---------------------------------------------------------------------------- ** Obsolete normative reference: RFC 1944 (Obsoleted by RFC 2544) Summary: 1 error (**), 0 flaws (~~), 2 warnings (==), 3 comments (--). Run idnits with the --verbose option for more detailed information about the items above. -------------------------------------------------------------------------------- 2 Network Working Group A. Morton 3 Internet-Draft AT&T Labs 4 Updates: 2544 (if approved) May 19, 2020 5 Intended status: Informational 6 Expires: November 20, 2020 8 Updates for the Back-to-back Frame Benchmark in RFC 2544 9 draft-ietf-bmwg-b2b-frame-02 11 Abstract 13 Fundamental Benchmarking Methodologies for Network Interconnect 14 Devices of interest to the IETF are defined in RFC 2544. This memo 15 updates the procedures of the test to measure the Back-to-back frames 16 Benchmark of RFC 2544, based on further experience. 18 This memo updates Section 26.4 of RFC 2544. 20 Requirements Language 22 The key words "MUST", "MUST NOT", "REQUIRED", "SHALL", "SHALL NOT", 23 "SHOULD", "SHOULD NOT", "RECOMMENDED", "NOT RECOMMENDED", "MAY", and 24 "OPTIONAL" in this document are to be interpreted as described in BCP 25 14[RFC2119] [RFC8174] when, and only when, they appear in all 26 capitals, as shown here. 28 Status of This Memo 30 This Internet-Draft is submitted in full conformance with the 31 provisions of BCP 78 and BCP 79. 33 Internet-Drafts are working documents of the Internet Engineering 34 Task Force (IETF). Note that other groups may also distribute 35 working documents as Internet-Drafts. The list of current Internet- 36 Drafts is at https://datatracker.ietf.org/drafts/current/. 38 Internet-Drafts are draft documents valid for a maximum of six months 39 and may be updated, replaced, or obsoleted by other documents at any 40 time. It is inappropriate to use Internet-Drafts as reference 41 material or to cite them other than as "work in progress." 43 This Internet-Draft will expire on November 20, 2020. 45 Copyright Notice 47 Copyright (c) 2020 IETF Trust and the persons identified as the 48 document authors. All rights reserved. 50 This document is subject to BCP 78 and the IETF Trust's Legal 51 Provisions Relating to IETF Documents 52 (https://trustee.ietf.org/license-info) in effect on the date of 53 publication of this document. Please review these documents 54 carefully, as they describe your rights and restrictions with respect 55 to this document. Code Components extracted from this document must 56 include Simplified BSD License text as described in Section 4.e of 57 the Trust Legal Provisions and are provided without warranty as 58 described in the Simplified BSD License. 60 Table of Contents 62 1. Introduction . . . . . . . . . . . . . . . . . . . . . . . . 2 63 2. Scope and Goals . . . . . . . . . . . . . . . . . . . . . . . 3 64 3. Motivation . . . . . . . . . . . . . . . . . . . . . . . . . 4 65 4. Prerequisites . . . . . . . . . . . . . . . . . . . . . . . . 6 66 5. Back-to-back Frames . . . . . . . . . . . . . . . . . . . . . 7 67 5.1. Preparing the list of Frame sizes . . . . . . . . . . . . 7 68 5.2. Test for a Single Frame Size . . . . . . . . . . . . . . 7 69 5.3. Test Repetition and Benchmark . . . . . . . . . . . . . . 9 70 5.4. Benchmark Calculations . . . . . . . . . . . . . . . . . 9 71 6. Reporting . . . . . . . . . . . . . . . . . . . . . . . . . . 10 72 7. Security Considerations . . . . . . . . . . . . . . . . . . . 11 73 8. IANA Considerations . . . . . . . . . . . . . . . . . . . . . 12 74 9. Acknowledgements . . . . . . . . . . . . . . . . . . . . . . 12 75 10. References . . . . . . . . . . . . . . . . . . . . . . . . . 12 76 10.1. Normative References . . . . . . . . . . . . . . . . . . 12 77 10.2. Informative References . . . . . . . . . . . . . . . . . 13 78 Author's Address . . . . . . . . . . . . . . . . . . . . . . . . 14 80 1. Introduction 82 The IETF's fundamental Benchmarking Methodologies are defined 83 in[RFC2544], supported by the terms and definitions in [RFC1242], and 84 [RFC2544] actually obsoletes an earlier specification, [RFC1944]. 85 Over time, the benchmarking community has updated [RFC2544] several 86 times, including the Device Reset Benchmark [RFC6201], and the 87 important Applicability Statement [RFC6815] concerning use outside 88 the Isolated Test Environment (ITE) required for accurate 89 benchmarking. Other specifications implicitly update [RFC2544], such 90 as the IPv6 Benchmarking Methodologies in [RFC5180]. 92 Recent testing experience with the Back-to-back Frame test and 93 Benchmark in Section 26.4 of [RFC2544] indicates that an update is 94 warranted [OPNFV-2017] [VSPERF-b2b]. In particular, analysis of the 95 results indicates that buffers size matters when compensating for 96 disruptions in the software packet processor, and this finding 97 increases the importance of the Back-to-back frame characterization 98 described here. This memo describes additional rationale and 99 provides the updated method. 101 [RFC2544] provides its own Requirements Language consistent with 102 [RFC2119], since [RFC1944] predates [RFC2119]. Thus, the 103 requirements presented in this memo are expressed in [RFC2119] terms, 104 and intended for those performing/reporting laboratory tests to 105 improve clarity and repeatability, and for those designing devices 106 that facilitate these tests. 108 2. Scope and Goals 110 The scope of this memo is to define an updated method to 111 unambiguously perform tests, measure the benchmark(s), and report the 112 results for Back-to-back Frames (presently described Section 26.4 of 113 [RFC2544]). 115 The goal is to provide more efficient test procedures where possible, 116 and to expand reporting with additional interpretation of the 117 results. The tests described in this memo address the cases where 118 the maximum frame rate of a single ingress port cannot be transferred 119 to an egress port loss-free (for some frame sizes of interest). 121 [RFC2544] Benchmarks rely on test conditions with constant frame 122 sizes, with the goal of understanding what network device capability 123 has been tested. Tests with the smallest size stress the header 124 processing capacity, and tests with the largest size stress the 125 overall bit processing capacity. Tests with sizes in-between may 126 determine the transition between these two capacities. However, 127 conditions simultaneously sending multiple frame sizes, such as those 128 described in [RFC6985], MUST NOT be used in Back-to-back Frame 129 testing. 131 Section 3 of [RFC8239] describes buffer size testing for physical 132 networking devices in a Data Center. The [RFC8239] methods measure 133 buffer latency directly with traffic on multiple ingress ports that 134 overload an egress port on the Device Under Test (DUT), and are not 135 subject to the revised calculations presented in this memo. 136 Likewise, the methods of [RFC8239] SHOULD be used for test cases 137 where the egress port buffer is the known point of overload. 139 3. Motivation 141 Section 3.1 of [RFC1242] describes the rationale for the Back-to-back 142 Frames Benchmark. To summarize, there are several reasons that 143 devices on a network produce bursts of frames at the minimum allowed 144 spacing, and it is therefore worthwhile to understand the Device 145 Under Test (DUT) limit on the length of such bursts in practice. 146 Also, [RFC1242] states: 148 "Tests of this parameter are intended to determine the extent 149 of data buffering in the device." 151 After this test was defined, there have been occasional discussions 152 of the stability and repeatability of the results, both over time and 153 across labs. Fortunately, the Open Platform for Network Function 154 Virtualization (OPNFV) VSPERF project's Continuous Integration (CI) 155 testing routinely repeats Back-to-back Frame tests to verify that 156 test functionality has been maintained through development of the 157 test control programs. These tests were used as a basis to evaluate 158 stability and repeatability, even across lab set-ups when the test 159 platform was migrated to new DUT hardware at the end of 2016. 161 When the VSPERF CI results were examined [VSPERF-b2b], several 162 aspects of the results were considered notable: 164 1. Back-to-back Frame Benchmark was very consistent for some fixed 165 frame sizes, and somewhat variable for others. 167 2. The number of Back-to-back Frames with zero loss reported for 168 large frame sizes was unexpectedly long (translating to 30 169 seconds of buffer time), and no explanation or measurement limit 170 condition was indicated. It's important that the buffering time 171 was used in this analysis. The referenced testing [VSPERF-b2b] 172 and calculations produced buffer extents of 30 seconds for some 173 frame sizes, and clearly wrong in practice. On the other hand, a 174 result expressed only as a large number of Back-to-back Frames 175 does not permit such an easy comparison with reality. 177 3. Calculation of the extent of buffer time in the DUT helped to 178 explain the results observed with all frame sizes (for example, 179 some frame sizes cannot exceed the frame header processing rate 180 of the DUT and therefore no buffering occurs, therefore the 181 results depended on the test equipment and not the DUT). 183 4. It was found that the actual extent of buffer time in the DUT 184 could be estimated using results to measure the longest burst in 185 frames without loss and results from the Throughput tests 186 conducted according to Section 26.1 of [RFC2544]. It is apparent 187 that the DUT's frame processing rate empties the buffer during a 188 trial and tends to increase the "implied" buffer size estimate 189 (measured according to Section 26.4 of [RFC2544] because many 190 frames have left the buffer when the burst of frames ends). A 191 calculation using the Throughput measurement can reveal a 192 "corrected" buffer size estimate. 194 Further, if the Throughput tests of Section 26.1 of [RFC2544] are 195 conducted as a prerequisite test, the number of frame sizes required 196 for Back-to-back Frame Benchmarking can be reduced to one or more of 197 the small frame sizes, or the results for large frame sizes can be 198 noted as invalid in the results if tested anyway (these are the 199 larger frame sizes for which the back-to-back frame rate cannot 200 exceed the frame header processing rate of the DUT and little or no 201 buffering occurs). 203 [VSPERF-b2b] provides the details of the calculation to estimate the 204 actual buffer storage available in the DUT, using results from the 205 Throughput tests for each frame size, and the maximum theoretical 206 frame rate for the DUT links (which constrain the minimum frame 207 spacing). 209 In reality, there are many buffers and packet header processing steps 210 in a typical DUT. The simplified model used in these calculations 211 for the DUT includes a packet header processing function with limited 212 rate of operation, as shown below: 214 |------------ DUT --------| 215 Generator -> Ingress -> Buffer -> HeaderProc -> Egress -> Receiver 217 So, in the back2back frame testing: 219 1. The Ingress burst arrives at Max Theoretical Frame Rate, and 220 initially the frames are buffered. 222 2. The packet header processing function (HeaderProc) operates at 223 the "Measured Throughput" (Section 26.1 of [RFC2544]), removing 224 frames from the buffer (this is the best approximation we have). 226 3. Frames that have been processed are clearly not in the buffer, so 227 the Corrected DUT buffer time equation (Section 5.4) estimates 228 and removes the frames that the DUT forwarded on Egress during 229 the burst. We define buffer time as the number of Frames 230 occupying the buffer divided by the Maximum Theoretical Frame 231 Rate (on egress) for the Frame size under test. 233 4. A helpful concept is the buffer filling rate, which is the 234 difference between the Max Theoretical Frame Rate (ingress) and 235 the Measured Throughput (HeaderProc on egress). If the actual 236 buffer size in frames was known, the time to fill the buffer 237 during a measurement can be calculated using the filling rate as 238 a check on measurements. However, the Buffer in the model 239 represents many buffers of different sizes in the DUT data path. 241 Knowledge of approximate buffer storage size (in time or bytes) may 242 be useful to estimate whether frame losses will occur if DUT 243 forwarding is temporarily suspended in a production deployment, due 244 to an unexpected interruption of frame processing (an interruption of 245 duration greater than the estimated buffer would certainly cause lost 246 frames). In Section 5, the calculations for the correct buffer time 247 for the combination of offered load at Max Theoretical Frame Rate and 248 header processing speed at 100% of Measured Throughput. Other 249 combinations are possible, such as changing the percent of measured 250 Throughput to account for other processes reducing the header 251 processing rate. 253 The presentation of OPNFV VSPERF evaluation and development of 254 enhanced search alogorithms [VSPERF-BSLV] was discussed at IETF-102. 255 The enhancements are intended to compensate for transient inerrrupts 256 that may cause loss at near-Throughput levels of offered load. 257 Subsequent analysis of the results indicates that buffers within the 258 DUT can compensate for some interrupts, and this finding increases 259 the importance of the Back-to-back frame characterization described 260 here. 262 4. Prerequisites 264 The Test Setup MUST be consistent with Figure 1 of [RFC2544], or 265 Figure 2 when the tester's sender and receiver are different devices. 266 Other mandatory testing aspects described in [RFC2544] MUST be 267 included, unless explicitly modified in the next section. 269 The ingress and egress link speeds and link layer protocols MUST be 270 specified and used to compute the maximum theoretical frame rate when 271 respecting the minimum inter-frame gap. 273 The test results for the Throughput Benchmark conducted according to 274 Section 26.1 of [RFC2544] for all [RFC2544]-RECOMMENDED frame sizes 275 MUST be available to reduce the tested frame size list, or to note 276 invalid results for individual frame sizes (because the burst length 277 may be essentially infinite for large frame sizes). 279 Note that: 281 o the Throughput and the Back-to-back Frame measurement 282 configuration traffic characteristics (unidirectional or bi- 283 directional) MUST match. 285 o the Throughput measurement MUST be under zero-loss conditions, 286 according to Section 26.1 of [RFC2544]. 288 The Back-to-back Benchmark described in Section 3.1 of [RFC1242] MUST 289 be measured directly by the tester, where buffer size is inferred 290 from Back-to-back Frame bursts and associated packet loss 291 measurements. Therefore, sources of packet loss that are un-related 292 to consistent evaluation of buffer size SHOULD be identified and 293 removed or mitigated. Example sources include: 295 o On-path active components that are external to the DUT 297 o Operating system environment interrupting DUT operation 299 o Shared resource contention between the DUT and other off-path 300 component(s) impacting DUT's behaviour, sometimes called the 301 "noisy neighbour" problem with virtualized network functions. 303 Mitigations applicable to some of the sources above are discussed in 304 Section 5.2, with the other measurement requirements described below 305 in Section 5. 307 5. Back-to-back Frames 309 Objective: To characterize the ability of a DUT to process back-to- 310 back frames as defined in [RFC1242]. 312 The Procedure follows. 314 5.1. Preparing the list of Frame sizes 316 From the list of RECOMMENDED Frame sizes (Section 9 of [RFC2544]), 317 select the subset of Frame sizes whose measured Throughput (during 318 prerequisite testing) was less than the maximum theoretical Frame 319 Rate of the DUT/test-set-up. These are the only Frame sizes where it 320 is possible to produce a burst of frames that cause the DUT buffers 321 to fill and eventually overflow, producing one or more discarded 322 frames. 324 5.2. Test for a Single Frame Size 326 Each trial in the test requires the tester to send a burst of frames 327 (after idle time) with the minimum inter-frame gap, and to count the 328 corresponding frames forwarded by the DUT. 330 The duration of the trial MUST be at least 2 seconds, to allow DUT 331 buffers to deplete. 333 If all frames have been received, the tester increases the length of 334 the burst according to the search algorithm and performs another 335 trial. 337 If the received frame count is less than the number of frames in the 338 burst, then the limit of DUT processing and buffering may have been 339 exceeded, and the burst length is determined by the search algorithm 340 for the next trial (the burst length is typically reduced, but see 341 below). 343 Classic search algorithms have been adapted for use in benchmarking, 344 where the search requires discovery of a pair of outcomes, one with 345 no loss and another with loss, at load conditions within the 346 acceptable tolerance or accuracy. Conditions encountered when 347 benchmarking the Infrastructure for Network Function Virtualization 348 require algorithm enhancement. Fortunately, the adaptation of Binary 349 Search, and an enhanced Binary Search with Loss Verification have 350 been specified in clause 12.3 of [TST009]. These alogorithms can 351 easily be used for Back-to-back Frame benchmarking by replacing the 352 Offered Load level with burst length in frames. [TST009] Annex B 353 describes the theory behind the enhanced Binary Search with Loss 354 Verification algorithm. 356 There is also promising work-in-progress that may prove useful in for 357 Back-to-back Frame benchmarking. 358 [I-D.vpolak-mkonstan-bmwg-mlrsearch] and [I-D.vpolak-bmwg-plrsearch] 359 are two such examples. 361 Either the [TST009] Binary Search or Binary Search with Loss 362 Verification algorithms MUST be used, and input parameters to the 363 algorithm(s) MUST be reported. 365 The tester usually imposes a (configurable) minimum step size for 366 burst length, and the step size MUST be reported with the results (as 367 this influences the accuracy and variation of test results). 369 The original Section 26.4 of [RFC2544] definition is stated below: 371 The Back-to-back Frame value is the longest burst of frames that 372 the DUT can successfully process and buffer without frame loss, as 373 determined from the series of trials. 375 5.3. Test Repetition and Benchmark 377 On this topic, Section 26.4 of [RFC2544] requires: 379 The trial length MUST be at least 2 seconds and SHOULD be repeated 380 at least 50 times with the average of the recorded values being 381 reported. 383 Therefore, the Benchmark for Back-to-back Frames is the average of 384 burst length values over repeated tests to determine the longest 385 burst of frames that the DUT can successfully process and buffer 386 without frame loss. Each of the repeated tests completes an 387 independent search process. 389 In this update, the test MUST be repeated N times (the number of 390 repetitions is now a variable that must be reported),for each frame 391 size in the subset list, and each Back-to-back Frame value made 392 available for further processing (below). 394 5.4. Benchmark Calculations 396 For each Frame size, calculate the following summary statistics for 397 longest Back-to-back Frame values over the N tests: 399 o Average (Benchmark) 401 o Minimum 403 o Maximum 405 o Standard Deviation 407 Further, calculate the Implied DUT Buffer Time and the Corrected DUT 408 Buffer Time in seconds, as follows: 410 Implied DUT Buffer Time = 412 Average num of Back-to-back Frames / Max Theoretical Frame Rate 414 The formula above is simply expressing the Burst of Frames in units 415 of time. 417 The next step is to apply a correction factor that accounts for the 418 DUT's frame forwarding operation during the test (assuming the simple 419 model of the DUT composed of a buffer and a forwarding function, 420 described in Section 3). 422 Corrected DUT Buffer Time = 423 / \ 424 Implied DUT |Implied DUT Measured Throughput | 425 = Buffer Time - |Buffer Time * -------------------------- | 426 | Max Theoretical Frame Rate | 427 \ / 429 where: 431 1. The "Measured Throughput" is the [RFC2544] Throughput Benchmark 432 for the frame size tested, as augmented by methods including the 433 Binary Search with Loss Verification aglorithm in [TST009] where 434 applicable, and MUST be expressed in Frames per second in this 435 equation. 437 2. The "Max Theoretical Frame Rate" is a calculated value for the 438 interface speed and link layer technology used, and MUST be 439 expressed in Frames per second in this equation. 441 The term on the far right in the formula for Corrected DUT Buffer 442 Time accounts for all the frames in the Burst that were transmitted 443 by the DUT *while the Burst of frames were sent in*. So, these frames 444 are not in the Buffer and the Buffer size is more accurately 445 estimated by excluding them. 447 6. Reporting 449 The back-to-back results SHOULD be reported in the format of a table 450 with a row for each of the tested frame sizes. There SHOULD be 451 columns for the frame size and for the resultant average frame count 452 for each type of data stream tested. 454 The number of tests Averaged for the Benchmark, N, MUST be reported. 456 The Minimum, Maximum, and Standard Deviation across all complete 457 tests SHOULD also be reported (they are referred to as 458 "Min,Max,StdDev" in the table below). 460 The Corrected DUT Buffer Time SHOULD also be reported. 462 If the tester operates using a limited maximum burst length in 463 frames, then this maximum length SHOULD be reported. 465 +--------------+----------------+----------------+------------------+ 466 | Frame Size, | Ave B2B | Min,Max,StdDev | Corrected Buff | 467 | octets | Length, frames | | Time, Sec | 468 +--------------+----------------+----------------+------------------+ 469 | 64 | 26000 | 25500,27000,20 | 0.00004 | 470 +--------------+----------------+----------------+------------------+ 472 Back-to-Back Frame Results 474 Static and configuration parameters: 476 Number of test repetitions, N 478 Minimum Step Size (during searches), in frames. 480 If the tester has a specific (actual) frame rate of interest (less 481 than the Throughput rate), it is useful to estimate the buffer time 482 at that actual frame rate: 484 Actual Buffer Time = 485 Max Theoretical Frame Rate 486 = Corrected DUT Buffer Time * -------------------------- 487 Actual Frame Rate 489 and report this value, properly labeled. 491 7. Security Considerations 493 Benchmarking activities as described in this memo are limited to 494 technology characterization using controlled stimuli in a laboratory 495 environment, with dedicated address space and the other constraints 496 of[RFC2544]. 498 The benchmarking network topology will be an independent test setup 499 and MUST NOT be connected to devices that may forward the test 500 traffic into a production network, or misroute traffic to the test 501 management network. See [RFC6815]. 503 Further, benchmarking is performed on a "black-box" basis, relying 504 solely on measurements observable external to the DUT/SUT. 506 Special capabilities SHOULD NOT exist in the DUT/SUT specifically for 507 benchmarking purposes. Any implications for network security arising 508 from the DUT/SUT SHOULD be identical in the lab and in production 509 networks. 511 8. IANA Considerations 513 This memo makes no requests of IANA. 515 9. Acknowledgements 517 Thanks to Trevor Cooper, Sridhar Rao, and Martin Klozik of the VSPERF 518 project for many contributions to the testing [VSPERF-b2b]. Yoshiaki 519 Itou has also investigated the topic, and made useful suggestions. 520 Maciek Konstantyowicz and Vratko Polak also provided many comments 521 and suggestions based on extensive integration testing and resulting 522 search algorithm proposals - the most up-to-date feedback possible. 523 Tim Carlin also provided comments and support for the draft. 525 10. References 527 10.1. Normative References 529 [RFC1242] Bradner, S., "Benchmarking Terminology for Network 530 Interconnection Devices", RFC 1242, DOI 10.17487/RFC1242, 531 July 1991, . 533 [RFC1944] Bradner, S. and J. McQuaid, "Benchmarking Methodology for 534 Network Interconnect Devices", RFC 1944, 535 DOI 10.17487/RFC1944, May 1996, 536 . 538 [RFC2119] Bradner, S., "Key words for use in RFCs to Indicate 539 Requirement Levels", BCP 14, RFC 2119, 540 DOI 10.17487/RFC2119, March 1997, 541 . 543 [RFC2544] Bradner, S. and J. McQuaid, "Benchmarking Methodology for 544 Network Interconnect Devices", RFC 2544, 545 DOI 10.17487/RFC2544, March 1999, 546 . 548 [RFC5180] Popoviciu, C., Hamza, A., Van de Velde, G., and D. 549 Dugatkin, "IPv6 Benchmarking Methodology for Network 550 Interconnect Devices", RFC 5180, DOI 10.17487/RFC5180, May 551 2008, . 553 [RFC6201] Asati, R., Pignataro, C., Calabria, F., and C. Olvera, 554 "Device Reset Characterization", RFC 6201, 555 DOI 10.17487/RFC6201, March 2011, 556 . 558 [RFC6815] Bradner, S., Dubray, K., McQuaid, J., and A. Morton, 559 "Applicability Statement for RFC 2544: Use on Production 560 Networks Considered Harmful", RFC 6815, 561 DOI 10.17487/RFC6815, November 2012, 562 . 564 [RFC6985] Morton, A., "IMIX Genome: Specification of Variable Packet 565 Sizes for Additional Testing", RFC 6985, 566 DOI 10.17487/RFC6985, July 2013, 567 . 569 [RFC8174] Leiba, B., "Ambiguity of Uppercase vs Lowercase in RFC 570 2119 Key Words", BCP 14, RFC 8174, DOI 10.17487/RFC8174, 571 May 2017, . 573 10.2. Informative References 575 [I-D.vpolak-bmwg-plrsearch] 576 Konstantynowicz, M. and V. Polak, "Probabilistic Loss 577 Ratio Search for Packet Throughput (PLRsearch)", draft- 578 vpolak-bmwg-plrsearch-03 (work in progress), March 2020. 580 [I-D.vpolak-mkonstan-bmwg-mlrsearch] 581 Konstantynowicz, M. and V. Polak, "Multiple Loss Ratio 582 Search for Packet Throughput (MLRsearch)", draft-vpolak- 583 mkonstan-bmwg-mlrsearch-03 (work in progress), March 2020. 585 [OPNFV-2017] 586 Cooper, T., Morton, A., and S. Rao, "Dataplane 587 Performance, Capacity, and Benchmarking in OPNFV", June 588 2017, 589 . 592 [RFC8239] Avramov, L. and J. Rapp, "Data Center Benchmarking 593 Methodology", RFC 8239, DOI 10.17487/RFC8239, August 2017, 594 . 596 [TST009] Morton, R. A., "ETSI GS NFV-TST 009 V3.2.1 (2019-06), 597 "Network Functions Virtualisation (NFV) Release 3; 598 Testing; Specification of Networking Benchmarks and 599 Measurement Methods for NFVI"", June 2019, 600 . 603 [VSPERF-b2b] 604 Morton, A., "Back2Back Testing Time Series (from CI)", 605 June 2017, . 609 [VSPERF-BSLV] 610 Morton, A. and S. Rao, "Evolution of Repeatability in 611 Benchmarking: Fraser Plugfest (Summary for IETF BMWG)", 612 July 2018, 613 . 617 Author's Address 619 Al Morton 620 AT&T Labs 621 200 Laurel Avenue South 622 Middletown,, NJ 07748 623 USA 625 Phone: +1 732 420 1571 626 Fax: +1 732 368 1192 627 Email: acmorton@att.com