Re: [Bloat] Another passive bandwidth estimation method
Hi Dave, well, I don't see DSCD as a competitor with cake or fq-pie. DSCD is not primarily an aqm mechanism but its central objective is prioritizing ABE traffic without harming BE traffic. This idea is more than 20 years old, but scalable algorithms were not available, DSCD fills this gap. However, some implementation details of DSCD may be useful for other aqm mechanisms or scheduling mechanisms, e.g., when it comes to rate calculation etc. Kind regards Michael Am 01.08.2023 um 10:37 schrieb Dave Taht: On Tue, Aug 1, 2023 at 1:24 AM Michael Menth wrote: Hi all, here is a private copy for personal use: http://atlas.cs.uni-tuebingen.de/menth/papers/Menth21-Sub-6-accepted.pdf Very interesting, thank you. So great you have code on github! I appreciate the mention of cake, and I figure it would scale worse than fq-pie in the 100Gbit scenario you present, but do not know. However, it does come with a built in forground (respecting EF, and a few other diffserv codepoints), and a background service class, respecting both CS1 and LE, and it would be interesting to know how that differs from DSCD? Kind regards Michael Am 01.08.2023 um 09:51 schrieb Sebastian Moeller: Hi Michael, that "teaser" you wrote is certainly interesting. Would you be able to distribute author copies to those of us that do not subscribe to IEEExplore, please? Regards Sebastian On Aug 1, 2023, at 09:32, Michael Menth via Bloat wrote: Hi all, we've recently developed a passive method for finding a link's capacity (in a different context). You find the algorithm in III.B.5 in https://ieeexplore.ieee.org/document/9954450 The approach ist tested in V.B for 1, 10, and 100 Gb/s links on a Linux server and provides sufficiently accurate results for bandwidth utilizations of 25%. The method is likely to work also for lower utilizations, but this was not an issue in this work. The method is applicable only by a link's head-end node. It does not work for end systems to find the bottleneck bandwidth on some unknown intermediate node. However, it can deliver useful information for scheduling algorithms in forwarding nodes, which is the use case in this paper, and which may be of interest to some readers on this list. Kind regards Michael Am 01.08.2023 um 00:36 schrieb Dave Taht via Bloat: Promising approach: https://ieeexplore.ieee.org/document/10188775 -- Prof. Dr. habil. Michael Menth University of Tuebingen Faculty of Science Department of Computer Science Chair of Communication Networks Sand 13, 72076 Tuebingen, Germany phone: (+49)-7071/29-70505 fax: (+49)-7071/29-5220 mailto:me...@uni-tuebingen.de http://kn.inf.uni-tuebingen.de ___ Bloat mailing list Bloat@lists.bufferbloat.net https://lists.bufferbloat.net/listinfo/bloat -- Prof. Dr. habil. Michael Menth University of Tuebingen Faculty of Science Department of Computer Science Chair of Communication Networks Sand 13, 72076 Tuebingen, Germany phone: (+49)-7071/29-70505 fax: (+49)-7071/29-5220 mailto:me...@uni-tuebingen.de http://kn.inf.uni-tuebingen.de -- Prof. Dr. habil. Michael Menth University of Tuebingen Faculty of Science Department of Computer Science Chair of Communication Networks Sand 13, 72076 Tuebingen, Germany phone: (+49)-7071/29-70505 fax: (+49)-7071/29-5220 mailto:me...@uni-tuebingen.de http://kn.inf.uni-tuebingen.de ___ Bloat mailing list Bloat@lists.bufferbloat.net https://lists.bufferbloat.net/listinfo/bloat
Re: [Bloat] Another passive bandwidth estimation method
On Tue, Aug 1, 2023 at 1:24 AM Michael Menth wrote: > > Hi all, > > here is a private copy for personal use: > > http://atlas.cs.uni-tuebingen.de/menth/papers/Menth21-Sub-6-accepted.pdf Very interesting, thank you. So great you have code on github! I appreciate the mention of cake, and I figure it would scale worse than fq-pie in the 100Gbit scenario you present, but do not know. However, it does come with a built in forground (respecting EF, and a few other diffserv codepoints), and a background service class, respecting both CS1 and LE, and it would be interesting to know how that differs from DSCD? > Kind regards > > Michael > > > Am 01.08.2023 um 09:51 schrieb Sebastian Moeller: > > Hi Michael, > > > > that "teaser" you wrote is certainly interesting. Would you be able to > > distribute author copies to those of us that do not subscribe to > > IEEExplore, please? > > > > Regards > > Sebastian > > > > > >> On Aug 1, 2023, at 09:32, Michael Menth via Bloat > >> wrote: > >> > >> Hi all, > >> > >> we've recently developed a passive method for finding a link's capacity > >> (in a different context). You find the algorithm in III.B.5 in > >> https://ieeexplore.ieee.org/document/9954450 > >> The approach ist tested in V.B for 1, 10, and 100 Gb/s links on a Linux > >> server and provides sufficiently accurate results for bandwidth > >> utilizations of 25%. The method is likely to work also for lower > >> utilizations, but this was not an issue in this work. The method is > >> applicable only by a link's head-end node. It does not work for end > >> systems to find the bottleneck bandwidth on some unknown intermediate > >> node. However, it can deliver useful information for scheduling algorithms > >> in forwarding nodes, which is the use case in this paper, and which may be > >> of interest to some readers on this list. > >> > >> Kind regards > >> > >> Michael > >> > >> > >> Am 01.08.2023 um 00:36 schrieb Dave Taht via Bloat: > >>> Promising approach: > >>> > >>> https://ieeexplore.ieee.org/document/10188775 > >> -- > >> Prof. Dr. habil. Michael Menth > >> University of Tuebingen > >> Faculty of Science > >> Department of Computer Science > >> Chair of Communication Networks > >> Sand 13, 72076 Tuebingen, Germany > >> phone: (+49)-7071/29-70505 > >> fax: (+49)-7071/29-5220 > >> mailto:me...@uni-tuebingen.de > >> http://kn.inf.uni-tuebingen.de > >> > >> ___ > >> Bloat mailing list > >> Bloat@lists.bufferbloat.net > >> https://lists.bufferbloat.net/listinfo/bloat > > -- > Prof. Dr. habil. Michael Menth > University of Tuebingen > Faculty of Science > Department of Computer Science > Chair of Communication Networks > Sand 13, 72076 Tuebingen, Germany > phone: (+49)-7071/29-70505 > fax: (+49)-7071/29-5220 > mailto:me...@uni-tuebingen.de > http://kn.inf.uni-tuebingen.de > -- Podcast: https://www.youtube.com/watch?v=bxmoBr4cBKg Dave Täht CSO, LibreQos ___ Bloat mailing list Bloat@lists.bufferbloat.net https://lists.bufferbloat.net/listinfo/bloat
Re: [Bloat] Another passive bandwidth estimation method
Hi all, here is a private copy for personal use: http://atlas.cs.uni-tuebingen.de/menth/papers/Menth21-Sub-6-accepted.pdf Kind regards Michael Am 01.08.2023 um 09:51 schrieb Sebastian Moeller: Hi Michael, that "teaser" you wrote is certainly interesting. Would you be able to distribute author copies to those of us that do not subscribe to IEEExplore, please? Regards Sebastian On Aug 1, 2023, at 09:32, Michael Menth via Bloat wrote: Hi all, we've recently developed a passive method for finding a link's capacity (in a different context). You find the algorithm in III.B.5 in https://ieeexplore.ieee.org/document/9954450 The approach ist tested in V.B for 1, 10, and 100 Gb/s links on a Linux server and provides sufficiently accurate results for bandwidth utilizations of 25%. The method is likely to work also for lower utilizations, but this was not an issue in this work. The method is applicable only by a link's head-end node. It does not work for end systems to find the bottleneck bandwidth on some unknown intermediate node. However, it can deliver useful information for scheduling algorithms in forwarding nodes, which is the use case in this paper, and which may be of interest to some readers on this list. Kind regards Michael Am 01.08.2023 um 00:36 schrieb Dave Taht via Bloat: Promising approach: https://ieeexplore.ieee.org/document/10188775 -- Prof. Dr. habil. Michael Menth University of Tuebingen Faculty of Science Department of Computer Science Chair of Communication Networks Sand 13, 72076 Tuebingen, Germany phone: (+49)-7071/29-70505 fax: (+49)-7071/29-5220 mailto:me...@uni-tuebingen.de http://kn.inf.uni-tuebingen.de ___ Bloat mailing list Bloat@lists.bufferbloat.net https://lists.bufferbloat.net/listinfo/bloat -- Prof. Dr. habil. Michael Menth University of Tuebingen Faculty of Science Department of Computer Science Chair of Communication Networks Sand 13, 72076 Tuebingen, Germany phone: (+49)-7071/29-70505 fax: (+49)-7071/29-5220 mailto:me...@uni-tuebingen.de http://kn.inf.uni-tuebingen.de ___ Bloat mailing list Bloat@lists.bufferbloat.net https://lists.bufferbloat.net/listinfo/bloat
Re: [Bloat] Another passive bandwidth estimation method
Hi Michael, that "teaser" you wrote is certainly interesting. Would you be able to distribute author copies to those of us that do not subscribe to IEEExplore, please? Regards Sebastian > On Aug 1, 2023, at 09:32, Michael Menth via Bloat > wrote: > > Hi all, > > we've recently developed a passive method for finding a link's capacity (in a > different context). You find the algorithm in III.B.5 in > https://ieeexplore.ieee.org/document/9954450 > The approach ist tested in V.B for 1, 10, and 100 Gb/s links on a Linux > server and provides sufficiently accurate results for bandwidth utilizations > of 25%. The method is likely to work also for lower utilizations, but this > was not an issue in this work. The method is applicable only by a link's > head-end node. It does not work for end systems to find the bottleneck > bandwidth on some unknown intermediate node. However, it can deliver useful > information for scheduling algorithms in forwarding nodes, which is the use > case in this paper, and which may be of interest to some readers on this list. > > Kind regards > > Michael > > > Am 01.08.2023 um 00:36 schrieb Dave Taht via Bloat: >> Promising approach: >> >> https://ieeexplore.ieee.org/document/10188775 > > -- > Prof. Dr. habil. Michael Menth > University of Tuebingen > Faculty of Science > Department of Computer Science > Chair of Communication Networks > Sand 13, 72076 Tuebingen, Germany > phone: (+49)-7071/29-70505 > fax: (+49)-7071/29-5220 > mailto:me...@uni-tuebingen.de > http://kn.inf.uni-tuebingen.de > > ___ > Bloat mailing list > Bloat@lists.bufferbloat.net > https://lists.bufferbloat.net/listinfo/bloat ___ Bloat mailing list Bloat@lists.bufferbloat.net https://lists.bufferbloat.net/listinfo/bloat
