555 karma · joined June 1, 2014
https://web.archive.org/web/20141217131407/http://icei.org/
But I do not want to talk about it, or how I feel about LF, the loss of GPL enforcement, the state of the embedded market, or the demise of linux journal, and of so many other ideals I still hold dear. I just keep plugging on, fixing bufferbloat, and home routers. Y'all caught me on a friday night, after a long week, trying to improve the cybersecurity label initiative at the FCC, as well as girding loins for yet another pointless battle over pointless points over network neutrality debate.
I really felt then, that misunderstood, and underappreciated, complicated, dedicated creators of really great code, would have a floor under them from all the companies that used it and did not understand it.
https://www.cnet.com/tech/tech-industry/late-ipo-change-left...
RHAT going public and sharing the IPO strike prices with the devs they based their success on, was a great day for the prospect of an indirect financial return on years of craftsmanship and care.
I hope one day, the idea finds new life.
He books were highly influential on me, and if it were not for his encouragement, and support, there would not be, oh, 10B copies of fq_codel running today, cake, or sqm, or better wifi routers, or libreqos.
We had fun, too!
http://esr.ibiblio.org/?p=4162
I did learn from his lesson - when he told me I had to be a front man for the bufferbloat effort, in 2013, for at least 5 years - he quoted the original of this:
“First they ignore you, then they laugh at you, then they fight you, then you win.” at me... and muttered under his breath,
"... and then you become a pariah."
I learned from his example.
So far, by staying on topic, and keeping my political and personal opinions out of any engagement with anyone on the web, and not writing controversial blogs (I know he has at least 3 he regrets)... I have largely escaped being a pariah, but, have also been working on fixing the same darn thing, for 7 years longer than I ever wanted to.
... but I like to think, that the awareness of the problem itself has propagated all the way up to the highest levels of many governments.
https://www.whitehouse.gov/briefing-room/statements-releases...
It is ok that the loadsharers idea, as conceived here, has died, as it lives on in other places, and the things that esr and I cared about then, are getting taken care of.
Eric himself, had a bout with stomach cancer, and has mostly withdrawn from the web, tired of the perpetual onslaught and criticism. He´s been working on a new book, for a very long time. IMHO he was the right person at the right time, to get open source into the mainstream, and although many might disagree with him, and his politics, I think his contribution to internet history is assured.
ESR´s most recent project was ntpsec.org, which vastly reduced the attack surface of ntp. Another key one used in many places, and needed less now, was reposurgeon: http://www.catb.org/esr/reposurgeon/repository-editing.html
https://twitter.com/jlivingood/status/1707078242857849244
With tons of links to all the technical activity it sparked since.
Seeing all the political activity tied onto it since (and now again) reminds me of two families at war about an incident that had happened generations and generations before, where the two sides no longer remembered why they hated each other so, but just went on hating, and not forgiving, and not moving on.
Yes, there are entirely separate and additional NN issues, but the technical problem of providing common carriage between two very different network application types (voip/gaming vs file transfer) is thoroughly solved now, and if only all sides recognised at least this much, and made peace over it, and worked together to deploy those solutions, maybe, just maybe, we could find mutually satisfactory solutions to the other problems that plague the internet today, like security, and the ipv6 rollout.
If anyone here knows anyone more political, still vibrating with 10+ years of outrage about NN on this fronts, on one side or the other, if you could sit them down, over a beer, and try to explain that at the start it was a technical problem nobody understood at the time, maybe that would help
but: Eric Dumazet came up with the flow queuing fast/slow queue concept in a single saturday afternoon in his hammock (after admittedly 9 months of hard work on every other fq and aqm algorithm), slammed it into the kernel the next day, and has been building ever more amazing things ever since.
I try to make sure people understand that I am more the acolyte of kathie, van, and Eric, than inventor here. I was proud of this thing we´d developed called SFQred, and writing a paper on it... but then kathie and van came out with codel a month later... obsoleting that part...
Eric and I implemented it over a week, saw that it was far better than RED... I went to sleep for a week, only to wake up to fq_codel, which solved everything.
We have been just re-implementing it and improving the edge cases since. I am pretty happy with cake, now. The world evolves however, and there are new demands on queuing. I cover some of these here: https://docs.google.com/document/d/1tTYBPeaRdCO9AGTGQCpoiuLO...
src here: https://github.com/LibreQoE/LibreQoS/
You can get a transparent high speed bridge with shaping capability up pretty rapidly with supported hardware.
I still long for an ethernet card that can do a trie lookup natively! The flamegraphs are mostly getting the right packet to the right cpu, still.
We have now produced variants of the flow queuing algorithm for fq-codel, fq-pie, and the FQ in cake, which we are now using in libreqos. It is the best form of fq ever designed, IMHO, with really good min/max fairness properties, resistence to starvation, great rtt fairness and highly complementary simultaneously time based AQM technology easily applied. I would like to see more improvements on the AQM side in the future and for it to land in more hardware.
Admittedly, I´m one of the authors... :)
FQ solves most of the problem thoroughly enabling delay based transports, Van and Kathie´s codel, most of the rest. Van was also on the team that produced BBR, which spends most of it´s time in delay based mode when fq_codel is on the path.
I do wish more folk were actively applying cake nowadays. It works wonders.
https://blog.cerowrt.org/post/juniper/
Libreqos is doing nice things with cake.
What would the internet have looked like without Van?
https://www.computerworld.com/article/2993112/vint-cerf-and-...
We were within months of delivering a massive RFC8290-based fix for wifi performance and we´d been bricking routers left and right... and then got in a whole bunch that we could not modify... due to that proposed regulation... I lost my temper, organized 260+ to sign, made that filing, won, and went back to work. I should perhaps have pressed harder, as the binary blob issue has got ever more terrifying, deeply embedded into too many baseband processors.
If I hold your attention a little bit? It would be rather nice if modern fq + aqm algorithms went into the internet nationwide. "Bufferbloat" is at epidemic proportions. Most the fixes arrived for it in Linux in 2012, and are only slowly rolling out 10+ years later, due to the accompanying epidemic of manufacturers´ not tracking new Linux kernels, (with all those accompanying vulnerabilities). I care very much about addressing security issues, but care about internet "latency under load" and better videoconferencing experiences more.
There´s only a billion or so devices left to upgrade.
https://www.usenix.org/system/files/conference/atc17/atc17-h...