Re: [Bloat] [Cerowrt-devel] plenty of huawei in the news today

2019-03-28 Thread David P. Reed
Yes, yes, yes, yes! Defense in depth is also good. We long ago learned that you don't design any large scale system without a lot of attention avoiding single-point catastrophes. One really major example is to achieve content protection with end-to-end security and authentication based on

Re: [Bloat] unfixable bloat on Cable modem CODA-4680 (puma 7)

2019-03-28 Thread cloneman
I have discovered the source of the confusion. This is different, but similar to PUMA6 problems, I think. Certain types of traffic are getting de-prioritized, especially small packets under load. Comparison: Normal ping: Minimum = 17ms, Maximum = 734ms, *Average = 202ms* Large 1472-byte ping

Re: [Bloat] [Cerowrt-devel] plenty of huawei in the news today

2019-03-28 Thread Valdis Klētnieks
On Thu, 28 Mar 2019 14:44:28 -0400, Jim Gettys said: > My solution is more radical: all the vendors should be held to much higher > standards, including reproducible builds (something that the UK government > has been trying to get them to do for years, and failed). All too often, even getting

Re: [Bloat] [Cerowrt-devel] plenty of huawei in the news today

2019-03-28 Thread Dave Taht
I share the reproducable builds thing - but for all vendors, including cisco and openwrt. Trust but verify. On Thu, Mar 28, 2019 at 11:44 AM Jim Gettys wrote: > > It's worth looking at the UK government oversight report: > >

Re: [Bloat] [Cerowrt-devel] plenty of huawei in the news today

2019-03-28 Thread Jim Gettys
It's worth looking at the UK government oversight report: https://assets.publishing.service.gov.uk/government/uploads/system/uploads/attachment_data/file/790270/HCSEC_OversightBoardReport-2019.pdf Not clear that Huawei is worse than other 5g vendors, if our experience with other embedded system

Re: [Bloat] [Cerowrt-devel] plenty of huawei in the news today

2019-03-28 Thread Dave Taht
I'd like to take the time to read this. https://assets.publishing.service.gov.uk/government/uploads/system/uploads/attachment_data/file/790270/HCSEC_OversightBoardReport-2019.pdf but I'm putting on a concert at 9. On Thu, Mar 28, 2019 at 11:32 AM David P. Reed wrote: > > Look, the existence

Re: [Bloat] [Cerowrt-devel] plenty of huawei in the news today

2019-03-28 Thread David P. Reed
Look, the existence of security flaws in software isn't news. Real news would be if there were systems discovered to have no flaws at all... So what does this article really say? It says that Britain and the US intelligence officials are now going after Huawei in a new way, because the

Re: [Bloat] [Cerowrt-devel] plenty of huawei in the news today

2019-03-28 Thread David P. Reed
The NYTimes has become a mouthpiece for those who want to see China as the new evil empire. Recent pieces by David Sanger have hyped the idea that the US has a "5G Gap" and that China (Huawei) will threaten to conquer the world with 5G superiority, so we should be vigilantly opposing Huawei.

Re: [Bloat] [Cerowrt-devel] plenty of huawei in the news today

2019-03-28 Thread Dave Taht
Well, it's a widely placed story in every newspaper. On Thu, Mar 28, 2019 at 11:16 AM David P. Reed wrote: > > The NYTimes has become a mouthpiece for those who want to see China as the > new evil empire. Recent pieces by David Sanger have hyped the idea that the > US has a "5G Gap" and that

[Bloat] plenty of huawei in the news today

2019-03-28 Thread Dave Taht
https://www.nytimes.com/2019/03/28/technology/huawei-security-british-report.html -- Dave Täht CTO, TekLibre, LLC http://www.teklibre.com Tel: 1-831-205-9740 ___ Bloat mailing list Bloat@lists.bufferbloat.net

Re: [Bloat] unfixable bloat on Cable modem CODA-4680 (puma 7)

2019-03-28 Thread Sebastian Moeller
HI cloneman, maybe have a look at http://www.dslreports.com/tools/puma6? > On Mar 28, 2019, at 12:00, cloneman wrote: > > I'm getting a weird problem with this new modem , it's Docsis 3.1 > > latency/jitter measured via ping is about ~300ms during download pressure of > 3 http transfers. The

Re: [Bloat] unfixable bloat on Cable modem CODA-4680 (puma 7)

2019-03-28 Thread Dave Taht
see badmodems.com On Thu, Mar 28, 2019 at 4:01 AM cloneman wrote: > > I'm getting a weird problem with this new modem , it's Docsis 3.1 > > latency/jitter measured via ping is about ~300ms during download pressure of > 3 http transfers. The latency doesn't appear on synthetic bufferbloat >

[Bloat] unfixable bloat on Cable modem CODA-4680 (puma 7)

2019-03-28 Thread cloneman
I'm getting a weird problem with this new modem , it's Docsis 3.1 latency/jitter measured via ping is about ~300ms during download pressure of 3 http transfers. The latency doesn't appear on synthetic bufferbloat benchmarks, though. (dslreports ; 20ms ("A") question: trying to figure out why I'm