Acee is talking propagation delay. Chris is talking transmission delay. Link delay is the sum of propagation and transmission delay. (Perhaps that clarification should be added to the draft?) But most ASICs have a minimum delay just to get the packet through the ASIC. The smallest numbers I have seen are around 200 nsec, and they are rare. This must be added to the transmission delay.
Cables can be quite short within a data center. See slide 8: https://www.ieee802.org/3/400GSG/public/13_11/booth_400_01a_1113.pdf But I don't think this technology is too interesting for use inside a data center, and even if it was rounding such links to 1 usec would probably be OK. As such, to me the 1 usec granularity looks OK. On Sun, May 23, 2021 at 6:12 PM Christian Hopps <cho...@chopps.org> wrote: > > "Acee Lindem (acee)" <acee=40cisco....@dmarc.ietf.org> writes: > > > Hi Greg, > > > > > > > > Additionally, in a vacuum light will only travel 300 meters in a > > microsecond. So, in a nanosecond, that is less than a foot. What > > transmission technology and application do you anticipate that will > > require this this precision? > > Off by a few magnitude; light travels just shy of 300,000,000 meters per > second. > > Consider that 100Gbps links transmit 100 bits every nanosecond. So about 5 > nanoseconds to send a minimum sized ethernet frame (sans the pre/postamble). > > Thanks, > Chris. > > > > > > > > > > Thanks, > > > > Acee > > > > > > > > From: Tony Li <tony1ath...@gmail.com> on behalf of Tony Li > > <tony...@tony.li> > > Date: Sunday, May 23, 2021 at 4:56 PM > > To: Greg Mirsky <gregimir...@gmail.com> > > Cc: Shraddha Hegde <shrad...@juniper.net>, "peng.sha...@zte.com.cn" > > <peng.sha...@zte.com.cn>, "lsr@ietf.org" <lsr@ietf.org>, > > "draft-hegde-lsr-flex-algo-bw-...@ietf.org" > > <draft-hegde-lsr-flex-algo-bw-...@ietf.org>, Acee Lindem > > <a...@cisco.com> > > Subject: Re: [Lsr] LSR WG Adoption Poll for "Flexible Algorithms: > > Bandwidth, Delay, Metrics and Constraints" - > > draft-hegde-lsr-flex-algo-bw-con-02 > > > > > > > > > > > > Hi Greg, > > > > > > > > That’s a very fair question and not one that has been discussed. > > > > > > > > Do we have that kind of accuracy from any of our measurement tools? > > Is that even on the horizon? I haven’t seen that… > > > > > > > > If it is time for nanosecond level measurement, then is it time to > > shift to floating point to give us more range? > > > > > > > > Tony > > > > > > > > On May 23, 2021, at 1:04 PM, Greg Mirsky <gregimir...@gmail.com> > > wrote: > > > > > > > > Hi Shraddha, Authors, et al., > > > > I apologize if my question has already been discussed. The unit > > for the maximum link delay in the draft is a microsecond. There > > is a group of services that require a highly accurate bounded > > delay. Have you considered using a nanosecond as the unit for the > > link delay? > > > > > > > > Regards, > > > > Greg > > > > > > > > On Wed, May 19, 2021 at 9:17 PM Shraddha Hegde <shraddha= > > 40juniper....@dmarc.ietf.org> wrote: > > > > Hi Pengshaofu, > > > > > > > > Pls see inline.. > > > > > > > > > > > > Juniper Business Use Only > > > > From: peng.sha...@zte.com.cn <peng.sha...@zte.com.cn> > > Sent: Thursday, May 20, 2021 7:26 AM > > To: Shraddha Hegde <shrad...@juniper.net> > > Cc: acee=40cisco....@dmarc.ietf.org; lsr@ietf.org; > > draft-hegde-lsr-flex-algo-bw-...@ietf.org > > Subject: Re:[Lsr] LSR WG Adoption Poll for "Flexible > > Algorithms: Bandwidth, Delay, Metrics and Constraints" - > > draft-hegde-lsr-flex-algo-bw-con-02 > > > > > > > > [External Email. Be cautious of content] > > > > > > > > > > > > Hi Shraddha, > > > > > > > > Thanks. Actually, I don't really want to define other metric > > types. > > > > Let's go back to the bandwidth-metric related to bandwidth > > capability. My worry is that bandwidth-metric (whether it is > > automatically calculated or manually configured) is not > > cumulative in nature, > > > > <Shraddha> Yes that is correct. > > > > which is different from IGP default metric/TE metric/delay > > metric, > > > > > > > > so that SPF based on bandwidth-metric may get an unexpected > > path (see the example of the original mail). > > > > Can more text be added in the draft to describe why this can > > work ? > > > > <Shraddha> Knowing that metric derived inversely from the > > link bandwidth is not additive in nature, should set the > > expectation right. I can add some text in this regard. > > > > > > > > Regards, > > > > PSF > > > > > > > > > > > > 原始邮件 > > > > 发件人：ShraddhaHegde > > > > 收件人：彭少富10053815; > > > > 抄送人：acee=40cisco....@dmarc.ietf.org;lsr@ietf.org; > > draft-hegde-lsr-flex-algo-bw-...@ietf.org; > > > > 日期：2021年05月18日 13:01 > > > > 主题：RE: Re:[Lsr] LSR WG Adoption Poll for "Flexible > > Algorithms: Bandwidth, Delay, Metrics and Constraints" - > > draft-hegde-lsr-flex-algo-bw-con-02 > > > > Hi Pengshaofu, > > > > > > > > If an operator wants to configure any other metric type draft > > provides a mechanism with generic metric. > > > > Generic metric allows any standard or user-defined type > > metric to be configured. > > > > The draft allows for any computing application such as > > Flex-algo, CSPF etc to make use of the > > > > Metric. The intention of the draft is that for a particular > > computation same metric-type is used > > > > throughout the network. If that is not clear, I’ll add some > > text in the draft. > > > > > > > > Using a combination of different metrics for a single > > computation would need significant change to SPF algorithm > > and it is not in the scope of the draft "Flexible Algorithms: > > Bandwidth, Delay, Metrics and Constraints". > > > > > > > > Hope that clarifies. > > > > > > > > Rgds > > > > Shraddha > > > > > > > > > > > > Juniper Business Use Only > > > > From: peng.sha...@zte.com.cn <peng.sha...@zte.com.cn> > > Sent: Monday, May 17, 2021 12:49 PM > > To: Shraddha Hegde <shrad...@juniper.net> > > Cc: acee=40cisco....@dmarc.ietf.org; lsr@ietf.org; > > draft-hegde-lsr-flex-algo-bw-...@ietf.org > > Subject: Re:[Lsr] LSR WG Adoption Poll for "Flexible > > Algorithms: Bandwidth, Delay, Metrics and Constraints" - > > draft-hegde-lsr-flex-algo-bw-con-02 > > > > > > > > [External Email. Be cautious of content] > > > > > > > > > > > > Hi Shraddha, > > > > > > > > The two methods of automatic generation of BW-metric > > introduced in the draft are also likely to be the method of > > manual configuration of BW-metric by operators. Operators > > can certainly manually configure any BW-metric he wants to > > configure. > > > > However, the manually configured BW-metric cannot deviate > > from the actual bandwidth capacity of the link, otherwise it > > could be any other names such as BX-metric. > > > > For manual assignment, the problem may still exist We can > > find an example that the accumulated bandwidth-metric on the > > path may offset the manually increased bandwidth-metric of > > links on the path. > > > > Combination of bandwidth attribute of link and other metric > > that is cumulative may be another co-exist way to completely > > address this issue. > > > > > > > > Regards, > > > > PSF > > > > > > > > > > > > > > > > > > > > 原始邮件 > > > > 发件人：ShraddhaHegde > > > > 收件人：彭少富10053815; > > > > 抄送人：acee=40cisco....@dmarc.ietf.org;lsr@ietf.org; > > draft-hegde-lsr-flex-algo-bw-...@ietf.org; > > > > 日期：2021年05月17日 12:15 > > > > 主题：RE: Re:[Lsr] LSR WG Adoption Poll for "Flexible > > Algorithms: Bandwidth, Delay, Metrics and Constraints" - > > draft-hegde-lsr-flex-algo-bw-con-02 > > > > Hi Pengshaofu, > > > > > > > > I was suggesting to manually assign bandwidth metric which > > will override the automatic metric calculation > > > > as described in the draft section 5. Physically adding more > > fiber/capacity is not a feasible solution. > > > > > > > > Rgds > > > > Shraddha > > > > > > > > > > > > Juniper Business Use Only > > > > From: peng.sha...@zte.com.cn <peng.sha...@zte.com.cn> > > Sent: Monday, May 17, 2021 7:40 AM > > To: Shraddha Hegde <shrad...@juniper.net> > > Cc: acee=40cisco....@dmarc.ietf.org; lsr@ietf.org; > > draft-hegde-lsr-flex-algo-bw-...@ietf.org > > Subject: Re:[Lsr] LSR WG Adoption Poll for "Flexible > > Algorithms: Bandwidth, Delay, Metrics and Constraints" - > > draft-hegde-lsr-flex-algo-bw-con-02 > > > > > > > > [External Email. Be cautious of content] > > > > > > > > > > > > Hi Shraddha, > > > > > > > > Thanks for your rely. > > > > So it seems that the scheme may lead to the selection of > > links with less bandwidth. To address this point, the method > > as you described to assign more bandwidth to high bandwidth > > links seems not always possible, e.g, adding more fiber ? > > > > Can this point can be addressed by combination of bandwidth > > attribute of link and other metric that is cumulative ? IMO, > > bandwidth is not cumulative. > > > > > > > > Regards > > > > PSF > > > > > > > > 原始邮件 > > > > 发件人：ShraddhaHegde > > > > 收件人：彭少富10053815; > > > > 抄送人：acee=40cisco....@dmarc.ietf.org;lsr@ietf.org; > > draft-hegde-lsr-flex-algo-bw-...@ietf.org; > > > > 日期：2021年05月13日 21:01 > > > > 主题：RE: Re:[Lsr] LSR WG Adoption Poll for "Flexible > > Algorithms: Bandwidth, Delay, Metrics and Constraints" - > > draft-hegde-lsr-flex-algo-bw-con-02 > > > > Hi Peng shaofu, > > > > > > > > As per the draft, if automatic metric calculation with > > reference bandwidth method is used to calculate the metric > > > > Then as per your example s->D path will be chosen since > > metric is 10. > > > > Lets say operator wants to choose S->X1->X2-àX10->D path then > > operator can manually assign higher bandwidth > > > > Metric on S->D link which will ensure S->D path is not the > > least cost path. > > > > > > > > Rgds > > > > Shraddha > > > > > > > > > > > > Juniper Business Use Only > > > > From: peng.sha...@zte.com.cn <peng.sha...@zte.com.cn> > > Sent: Thursday, May 13, 2021 1:05 PM > > To: peng.sha...@zte.com.cn > > Cc: acee=40cisco....@dmarc.ietf.org; lsr@ietf.org; > > draft-hegde-lsr-flex-algo-bw-...@ietf.org > > Subject: Re:[Lsr] LSR WG Adoption Poll for "Flexible > > Algorithms: Bandwidth, Delay, Metrics and Constraints" - > > draft-hegde-lsr-flex-algo-bw-con-02 > > > > > > > > [External Email. Be cautious of content] > > > > > > > > > > > > Sorry for spelling mistakens in the previous email. > > > > updated text: > > > > > > > > > > > > Hi WG, > > > > > > > > I have a little doubt about the scheme described in this > > document. > > > > See the following example: > > > > > > > > S ---- X1 ----- X2 ---- ... ... ----- X10 ----- D > > > > \----------------------------------------------/ > > > > > > > > Suppose the links in S---X1---X2...---D have the same > > bandwidth 10G, and the link S-D has bandwidth 1G. > > > > Suppose that we select "reference bandwidth = 100G", then, > > > > each link in S---X1---X2...---D will have the same > > bandwidth-metric 10 (i.e., 100/10) > > > > link S-D will have a bandwidth-metric 100 (i.e., 100/1) > > > > > > > > So flex-algo path from S to D based on bandwidth-metric will > > be S-D, not S---X1---X2...---D, because the later has a large > > cumulative bandwitdh-metric (i.e., 11*10). > > > > But our expect path should not be S-D, but > > S---X1---X2...---D, as it has large bandwidth. > > > > Do I misunderstand anything ? > > > > > > > > Regards, > > > > PSF > > > > > > > > > > > > > > > > > > > > 发件人：AceeLindem(acee) > > > > 收件人：lsr@ietf.org; > > > > 抄送人：draft-hegde-lsr-flex-algo-bw-...@ietf.org; > > > > 日期：2021年05月13日 05:49 > > > > 主题：[Lsr] LSR WG Adoption Poll for "Flexible Algorithms: > > Bandwidth, Delay, Metrics and Constraints" - > > draft-hegde-lsr-flex-algo-bw-con-02 > > > > _______________________________________________ > > Lsr mailing list > > Lsr@ietf.org > > https://www.ietf.org/mailman/listinfo/lsr > > > > Esteemed Members of the LSR WG, > > > > > > > > This begins a 2 week WG adoption call for the following > > draft: > > > > > > > > https://datatracker.ietf.org/doc/ > > draft-hegde-lsr-flex-algo-bw-con/ > > > > > > > > Please indicate your support or objection by May 27^th, 2021. > > > > > > > > Authors, please respond to the list indicating whether you > > are aware of any IPR that applies to this draft. > > > > > > > > Thanks, > > > > Chris and Acee > > > > > > > > > > > > > > > > > > > > > > > > > > > > _______________________________________________ > > Lsr mailing list > > Lsr@ietf.org > > https://www.ietf.org/mailman/listinfo/lsr > > > > > > > > > > > > _______________________________________________ > > Lsr mailing list > > Lsr@ietf.org > > https://www.ietf.org/mailman/listinfo/lsr > > _______________________________________________ > Lsr mailing list > Lsr@ietf.org > https://www.ietf.org/mailman/listinfo/lsr >
_______________________________________________ Lsr mailing list Lsr@ietf.org https://www.ietf.org/mailman/listinfo/lsr
