[ippm] Fw: [bmwg] New ID: Considerations for Interpret ing Packet Loss Observed by Active Performance Measurements
Libin Liu <[email protected]> Tue, 14 Jul 2026 01:54:05 +0000
| Newsgroups | gmane.ietf.ippm,gmane.ietf.bmwg |
|---|---|
| Message-ID | <TY4PR01MB126682191534E27A64ABFAAE8E2F92@TY4PR01MB12668.jpnprd01.prod.outlook.com> |
--===============0452512004284110262== Content-Language: en-US Content-Type: multipart/alternative; boundary="_000_TY4PR01MB126682191534E27A64ABFAAE8E2F92TY4PR01MB12668jp_" --_000_TY4PR01MB126682191534E27A64ABFAAE8E2F92TY4PR01MB12668jp_ Content-Type: text/plain; charset="iso-8859-1" Content-Transfer-Encoding: quoted-printable Dear All, Following my previous email, I would like to share a more detailed set of s= lides introducing draft-liu-ippm-active-loss-considerations. The presentati= on provides more background on the motivation, the interpretation problem, = and the overall framework discussed in the draft. The slides are available in the GitHub repo: https://github.com/LibinLiu018= 9/draft-ippm-active-loss-considerations/blob/main/slides-ippm-active-loss-c= onsiderations-00.pdf If the topic is of interest, I would appreciate any comments or feedback. I= would also be happy to discuss the work, either in Vienna during IETF 126 = or online. Thank you very much. Best, Libin ________________________________ From: Libin Liu <liulb=3D40zgclab.edu.cn-Tr9gZwTxerDR74oF6e/[email protected]> Sent: Thursday, July 2, 2026 9:30 AM To: [email protected] <[email protected]>; [email protected] <[email protected]> Subject: [bmwg] New ID: Considerations for Interpreting Packet Loss Observe= d by Active Performance Measurements Dear All, I would like to draw your attention to a new draft that has recently been s= ubmitted: draft-liu-ippm-active-measurement-loss-considerations-00. This document discusses considerations for interpreting packet loss observe= d by active performance measurements. While measurement protocols and metri= cs accurately report observable outcomes such as packet loss, missing respo= nses, delay, and delay variation, these observations alone often do not rev= eal the underlying operational cause. Similar measurement results may arise= from different conditions, including congestion, forwarding failures, rout= ing changes, filtering policies, endpoint behavior, multipath forwarding, o= r validation-related packet discard. The document proposes a common interpretation framework that distinguishes = measured outcomes from inferred causes. It discusses how different operatio= nal conditions may affect the interpretation of packet loss, delay, and del= ay variation in active performance measurements, including one-way and two-= way measurements, OWAMP, TWAMP, STAMP, and measurements over ECMP and link = aggregation. The document also discusses how additional operational context= may assist operators and measurement systems in reasoning about possible e= xplanations for observed measurement results. The draft is available here: = https://datatracker.ietf.org/doc/draft-liu-ippm-active-loss-considerations/= . The GitHub repository for the draft is also available here for issues, co= mments, and pull requests: https://github.com/LibinLiu0189/draft-ippm-activ= e-loss-considerations. Comments, suggestions, and discussions would be greatly appreciated. I woul= d also be interested to hear whether similar interpretation challenges have= been encountered in operational deployments or existing measurement system= s, and whether there are additional scenarios that should be considered in = the document. Thank you very much. Best, Libin > -----Original Messages----- > From: [email protected] > Send time:Wednesday, 01/07/2026 17:09:28 > To: "Libin Liu" <[email protected]> > Subject: New Version Notification for draft-liu-ippm-active-loss-consider= ations-00.txt > > A new version of Internet-Draft > draft-liu-ippm-active-loss-considerations-00.txt has been successfully > submitted by Libin Liu and posted to the > IETF repository. > > Name: draft-liu-ippm-active-loss-considerations > Revision: 00 > Title: Considerations for Interpreting Packet Loss Observed by Active = Performance Measurements > Date: 2026-07-01 > Group: Individual Submission > Pages: 30 > URL: https://www.ietf.org/archive/id/draft-liu-ippm-active-loss-cons= iderations-00.txt > Status: https://datatracker.ietf.org/doc/draft-liu-ippm-active-loss-con= siderations/ > HTML: https://www.ietf.org/archive/id/draft-liu-ippm-active-loss-cons= iderations-00.html > HTMLized: https://datatracker.ietf.org/doc/html/draft-liu-ippm-active-los= s-considerations > > > Abstract: > > Active performance measurement protocols and metrics are commonly > used to measure packet loss, delay, delay variation, reachability, > and path behavior. When an active measurement packet is not > received, a response is missing, or a measurement exchange times out, > the measurement result identifies the observable outcome but often > does not identify the underlying cause. > > Loss observed by active performance measurements can be associated > with congestion, queue discard, link or forwarding failures, routing > changes, endpoint or reflector behavior, administrative filtering, > policing, multipath effects, or validation-related packet discard > such as Source Address Validation (SAV). Different operational > conditions can produce similar measurement observations, but they may > have different meanings and require different troubleshooting > actions. > > This document discusses considerations for interpreting packet loss > observed by active performance measurements. It provides a common > set of considerations for separating measured outcomes from inferred > causes, describes operational conditions that can lead to observed > loss, discusses implications for one-way and two-way measurements, > delay and delay variation interpretation, OWAMP, TWAMP, STAMP, and > measurements over ECMP and link aggregation. It also discusses how > some considerations may apply to hybrid and passive performance > measurements and identifies sources of operational context that can > help operators and measurement systems reason about possible > explanations. > > > > The IETF Secretariat > _______________________________________________ bmwg mailing list -- [email protected] To unsubscribe send an email to [email protected] --_000_TY4PR01MB126682191534E27A64ABFAAE8E2F92TY4PR01MB12668jp_ Content-Type: text/html; charset="iso-8859-1" Content-Transfer-Encoding: quoted-printable <html> <head> <meta http-equiv=3D"Content-Type" content=3D"text/html; charset=3Diso-8859-= 1"> <style type=3D"text/css" style=3D"display:none;"> P {margin-top:0;margin-bo= ttom:0;} </style> </head> <body dir=3D"ltr"> <div class=3D"elementToProof" style=3D"font-family: Aptos, Aptos_EmbeddedFo= nt, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt; c= olor: rgb(0, 0, 0);"> Dear All,</div> <div class=3D"elementToProof" style=3D"font-family: Aptos, Aptos_EmbeddedFo= nt, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt; c= olor: rgb(0, 0, 0);"> <br> </div> <div class=3D"elementToProof" style=3D"font-family: Aptos, Aptos_EmbeddedFo= nt, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt; c= olor: rgb(0, 0, 0);"> Following my previous email, I would like to share a more detailed set of s= lides introducing draft-liu-ippm-active-loss-considerations. The presentati= on provides more background on the motivation, the interpretation problem, = and the overall framework discussed in the draft.</div> <div class=3D"elementToProof" style=3D"font-family: Aptos, Aptos_EmbeddedFo= nt, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt; c= olor: rgb(0, 0, 0);"> <br> </div> <div class=3D"elementToProof" style=3D"font-family: Aptos, Aptos_EmbeddedFo= nt, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt; c= olor: rgb(0, 0, 0);"> The slides are available in the GitHub repo: https://github.com/LibinLiu018= 9/draft-ippm-active-loss-considerations/blob/main/slides-ippm-active-loss-c= onsiderations-00.pdf</div> <div class=3D"elementToProof" style=3D"font-family: Aptos, Aptos_EmbeddedFo= nt, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt; c= olor: rgb(0, 0, 0);"> <br> </div> <div class=3D"elementToProof" style=3D"font-family: Aptos, Aptos_EmbeddedFo= nt, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt; c= olor: rgb(0, 0, 0);"> If the topic is of interest, I would appreciate any comments or feedback. I= would also be happy to discuss the work, either in Vienna during IETF 126 = or online.</div> <div class=3D"elementToProof" style=3D"font-family: Aptos, Aptos_EmbeddedFo= nt, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt; c= olor: rgb(0, 0, 0);"> <br> </div> <div class=3D"elementToProof" style=3D"font-family: Aptos, Aptos_EmbeddedFo= nt, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt; c= olor: rgb(0, 0, 0);"> Thank you very much.</div> <div class=3D"elementToProof" style=3D"font-family: Aptos, Aptos_EmbeddedFo= nt, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt; c= olor: rgb(0, 0, 0);"> <br> </div> <div class=3D"elementToProof" style=3D"font-family: Aptos, Aptos_EmbeddedFo= nt, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt; c= olor: rgb(0, 0, 0);"> <br> </div> <div class=3D"elementToProof" style=3D"font-family: Aptos, Aptos_EmbeddedFo= nt, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt; c= olor: rgb(0, 0, 0);"> Best,</div> <div style=3D"font-family: Aptos, Aptos_EmbeddedFont, Aptos_MSFontService, = Calibri, Helvetica, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);"> Libin</div> <div style=3D"font-family: Aptos, Aptos_EmbeddedFont, Aptos_MSFontService, = Calibri, Helvetica, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);"> <br> </div> <hr style=3D"display: inline-block; width: 98%;"> <div id=3D"divRplyFwdMsg"> <div style=3D"direction: ltr; font-family: Calibri, sans-serif; font-size: = 11pt; color: rgb(0, 0, 0);"> <b>From:</b> Libin Liu <liulb=3D40zgclab.edu.cn-Tr9gZwTxerDR74oF6e/[email protected]><br> <b>Sent:</b> Thursday, July 2, 2026 9:30 AM<br> <b>To:</b> [email protected] <[email protected]>; [email protected] <bmwg@ietf= .org><br> <b>Subject:</b> [bmwg] New ID: Considerations for Interpreting Packet Loss = Observed by Active Performance Measurements</div> <div style=3D"direction: ltr;"> </div> </div> <div style=3D"font-size: 11pt;">Dear All,<br> <br> I would like to draw your attention to a new draft that has recently been s= ubmitted: draft-liu-ippm-active-measurement-loss-considerations-00.<br> <br> This document discusses considerations for interpreting packet loss observe= d by active performance measurements. While measurement protocols and metri= cs accurately report observable outcomes such as packet loss, missing respo= nses, delay, and delay variation, these observations alone often do not reveal the underlying operational ca= use. Similar measurement results may arise from different conditions, inclu= ding congestion, forwarding failures, routing changes, filtering policies, = endpoint behavior, multipath forwarding, or validation-related packet discard. <br> <br> The document proposes a common interpretation framework that distinguishes = measured outcomes from inferred causes. It discusses how different operatio= nal conditions may affect the interpretation of packet loss, delay, and del= ay variation in active performance measurements, including one-way and two-way measurements, OWAMP, TWAMP, ST= AMP, and measurements over ECMP and link aggregation. The document also dis= cusses how additional operational context may assist operators and measurem= ent systems in reasoning about possible explanations for observed measurement results. The draft is available here= : <a href=3D"https://datatracker.ietf.org/doc/draft-liu-ippm-active-loss-co= nsiderations/" id=3D"OWAef180334-9f28-8286-776a-fe8a8bb522fa" class=3D"OWAA= utoLink" data-auth=3D"NotApplicable"> https://datatracker.ietf.org/doc/draft-liu-ippm-active-loss-considerations/= </a>. The GitHub repository for the draft is also available here for issues= , comments, and pull requests: <a href=3D"https://github.com/LibinLiu0189/draft-ippm-active-loss-considera= tions" id=3D"OWA654dcfab-3de6-0ae2-dcdf-2a77ebb1b3b0" class=3D"OWAAutoLink"= data-auth=3D"NotApplicable"> https://github.com/LibinLiu0189/draft-ippm-active-loss-considerations</a>.<= br> <br> Comments, suggestions, and discussions would be greatly appreciated. I woul= d also be interested to hear whether similar interpretation challenges have= been encountered in operational deployments or existing measurement system= s, and whether there are additional scenarios that should be considered in the document.<br> <br> Thank you very much.<br> <br> <br> Best,<br> Libin<br> <br> > -----Original Messages-----<br> > From: [email protected]<br> > Send time:Wednesday, 01/07/2026 17:09:28<br> > To: "Libin Liu" <[email protected]><br> > Subject: New Version Notification for draft-liu-ippm-active-loss-consi= derations-00.txt<br> ><br> > A new version of Internet-Draft<br> > draft-liu-ippm-active-loss-considerations-00.txt has been successfully= <br> > submitted by Libin Liu and posted to the<br> > IETF repository.<br> ><br> > Name: draft-liu-ippm-active-loss-consideration= s<br> > Revision: 00<br> > Title: Considerations for Interpreting Packet Loss O= bserved by Active Performance Measurements<br> > Date: 2026-07-01<br> > Group: Individual Submission<br> > Pages: 30<br> > URL: <a href=3D"https://www.ietf.org/arc= hive/id/draft-liu-ippm-active-loss-considerations-00.txt" id=3D"OWA9369c40d= -edd9-85b8-6642-33f07e6982a1" class=3D"OWAAutoLink" data-auth=3D"NotApplica= ble"> https://www.ietf.org/archive/id/draft-liu-ippm-active-loss-considerations-0= 0.txt</a><br> > Status: <a href=3D"https://datatracker.ietf.org/doc/draft-= liu-ippm-active-loss-considerations/" id=3D"OWA792dbb33-43d0-9c8c-0158-8607= add3f1a2" class=3D"OWAAutoLink" data-auth=3D"NotApplicable"> https://datatracker.ietf.org/doc/draft-liu-ippm-active-loss-considerations/= </a><br> > HTML: <a href=3D"https://www.ietf.org/archive/= id/draft-liu-ippm-active-loss-considerations-00.html" id=3D"OWA2e411b6e-814= b-ccea-0fb5-d26f477238be" class=3D"OWAAutoLink" data-auth=3D"NotApplicable"= > https://www.ietf.org/archive/id/draft-liu-ippm-active-loss-considerations-0= 0.html</a><br> > HTMLized: <a href=3D"https://datatracker.ietf.org/doc/html/draft-liu-i= ppm-active-loss-considerations" id=3D"OWA21ebb65d-741e-a3c2-e213-bbe5a66706= ff" class=3D"OWAAutoLink" data-auth=3D"NotApplicable"> https://datatracker.ietf.org/doc/html/draft-liu-ippm-active-loss-considerat= ions</a><br> ><br> ><br> > Abstract:<br> ><br> > Active performance measurement protocols and metrics= are commonly<br> > used to measure packet loss, delay, delay variation,= reachability,<br> > and path behavior. When an active measurement = packet is not<br> > received, a response is missing, or a measurement ex= change times out,<br> > the measurement result identifies the observable out= come but often<br> > does not identify the underlying cause.<br> ><br> > Loss observed by active performance measurements can= be associated<br> > with congestion, queue discard, link or forwarding f= ailures, routing<br> > changes, endpoint or reflector behavior, administrat= ive filtering,<br> > policing, multipath effects, or validation-related p= acket discard<br> > such as Source Address Validation (SAV). Diffe= rent operational<br> > conditions can produce similar measurement observati= ons, but they may<br> > have different meanings and require different troubl= eshooting<br> > actions.<br> ><br> > This document discusses considerations for interpret= ing packet loss<br> > observed by active performance measurements. I= t provides a common<br> > set of considerations for separating measured outcom= es from inferred<br> > causes, describes operational conditions that can le= ad to observed<br> > loss, discusses implications for one-way and two-way= measurements,<br> > delay and delay variation interpretation, OWAMP, TWA= MP, STAMP, and<br> > measurements over ECMP and link aggregation. I= t also discusses how<br> > some considerations may apply to hybrid and passive = performance<br> > measurements and identifies sources of operational c= ontext that can<br> > help operators and measurement systems reason about = possible<br> > explanations.<br> ><br> ><br> ><br> > The IETF Secretariat<br> ><br> _______________________________________________<br> bmwg mailing list -- [email protected]<br> To unsubscribe send an email to [email protected]</div> </body> </html> --_000_TY4PR01MB126682191534E27A64ABFAAE8E2F92TY4PR01MB12668jp_-- --===============0452512004284110262== Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: base64 Content-Disposition: inline X19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX18KaXBwbSBtYWls aW5nIGxpc3QgLS0gaXBwbUBpZXRmLm9yZwpUbyB1bnN1YnNjcmliZSBzZW5kIGFuIGVtYWlsIHRv IGlwcG0tbGVhdmVAaWV0Zi5vcmcK --===============0452512004284110262==--