Top all-time · #4127
Dave Taht
Personal blog · blog.cerowrt.orgsystemshardware
Dave Taht writes CeroWrt notebook: On fixing the internet since 2011, a personal blog at blog.cerowrt.org about systems and hardware. Since 2016, 19 different Hacker News readers have linked it 46 times, most often “Flaws and features in the Flent network testing tool”. The last post was in 2024, but the archive is still widely read.
Too few sampled comments (6) to say how often HN recommends it.?
Why HN links it
HN readers link Dave Taht's cerowrt blog as a reference on bufferbloat and fq_codel queue management, covering ISP queuing, Wi-Fi channel scans and fair queuing. Posts are cited as supporting evidence.
Summarised by Claude from a sample of 6 HN comments that link here. Each comment is marked recommending, critical or neutral (citing without judging); how this works.
Most-linked posts?
- Flaws and features in the Flent network testing tool3 people · 5 mentions · first linked 2023-01-16
- The state of fq_codel and cake in 20223 people · 3 mentions · first linked 2022-04-24
- Bufferbloat on the Internet backbone3 people · 3 mentions · first linked 2017-11-13
- New features and flaws of speedtest.net and Cloudflare2 people · 3 mentions · first linked 2023-01-12
- Solving the crypto-fq bug in ath9k (2016)2 people · 2 mentions · first linked 2016-09-16
- Sane Uses for Fiber2 people · 2 mentions · first linked 2023-07-13
- Net Neutrality advocates: Care to try some technical solutions instead?2 people · 2 mentions · first linked 2018-06-21
What Hacker News says?
I have long worried that net neutrality rules mis-applied would prevent the default availability of quality fair queuing and AQM solutions along the edge of the network. https://blog.cerowrt.org/post/net_neutrality_customers/ https://blog.apnic.net/2020/01/22/bufferbloat-may-be-solved-...
Comment linking /post/net_neutrality_customers/
on “Ask HN: Internet magically gets faster when opening speedtest?”Submitted Solving the crypto-fq bug in ath9k (2016) as a story · 38 points
HN discussionExcessive channel scans have been a problem on Linux, too: http://blog.cerowrt.org/post/disabling_channel_scans/
Comment linking /post/disabling_channel_scans/
on “Google unveils Stadia cloud gaming service”Submitted The state of fq_codel and cake in 2022 as a story · 30 points
HN discussionIt seems like everything with buffer/process queues needs a good polish to optimize for fairness. E.g. this is just being readied: http://blog.cerowrt.org/post/fq_codel_on_ath10k/ (also note higher throughput as result)
Comment linking /post/fq_codel_on_ath10k/
on “The Linux Scheduler: A Decade of Wasted Cores [pdf]”Submitted Space travel via tether between asteroids as a story · 8 points
HN discussionhttps://en.wikipedia.org/wiki/Dave_T%C3%A4ht https://blog.cerowrt.org/ https://lists.bufferbloat.net/pipermail/bloat/2025-April/018...
Comment linking /
on “Dave Täht has died”Submitted The state of `fq_codel` and `sch_cake` worldwide (2022) as a story · 4 points
HN discussionGlad you use irtt! More should! The bufferbloat project does maintain a few public IRTT servers around the world: https://blog.cerowrt.org/post/flent_fleet/ It would be great to add more to the pool.
Comment linking /post/flent_fleet/
on “New FCC Broadband Standards Should Consider Latency”Submitted New features and flaws of speedtest.net and Cloudflare as a story · 4 points
HN discussionThe biggest thing that makes me nuts about our speedtest regimes is that we test upload and download separately, rather than at the same time. People have 16+ wifi devices on their networks today. There IS upstream traffic going on at the same time, most of the time, and what happens when one side or the other also saturated or merely in use is widely misunderstood. For example a short packet fifo on the uplink star…
Comment linking /post/towards_better_broadband/
on “New FCC Broadband Standards Should Consider Latency”Submitted Blinkinlights Are a Curse as a story · 3 points
HN discussionBufferbloat happens on high speed links like those but amount of bloat you see is in the 30ms - 60ms range (vs seconds(!!) on home links). Bloat happens mostly (aside from microbursts) on overloaded links - and high speed backbones are typically overprovisioned so the problem only shows up when there's an outage or fiber cut. Example of what happens today on a fiber cut: http://blog.cerowrt.org/post/bufferbloat_on_t…
Comment linking /post/bufferbloat_on_the_backbone/
on “What Can I Do About Bufferbloat?”Submitted Bufferbloat on the Internet backbone as a story · 3 points
HN discussionRecently I ranted at the ISPs and at the network neutrality people. fq_codel (RFC8290) is now nearly ubiquitous in as the default queuing mechanism in most linux distributions, and it is long past time more ISPs supplied it in the gear they give customers. http://blog.cerowrt.org/post/net_neutrality_customers/ sch_cake (derived from fq_codel with an integral shaper) is about to enter the Linux mainline after years o…
Comment linking /post/net_neutrality_customers/
on “What Can I Do About Bufferbloat?”Submitted A quick look at TCP BBR as a story · 3 points
HN discussionReally good thread. Several comments: Flow Queuing allows applications not creating queues to bypass those that are. It is mildly different from fair queuing: https://ieeexplore.ieee.org/document/8469111 Load shedding, at least for packets, benefits from head drop more than tail drop. Only the codel algorithm does this but codel has been applied to other forms of queuing like Uber dealing with a concertgoer overload…
Comment linking /post/juniper/
on “Queues don't fix overload (2014)”Submitted Sane Uses for Fiber as a story · 2 points
HN discussionToo bitter. I referenced a little of that "adventure" here, in 2021... gfiber was attempting to restart with refreshing their now obsolete hardware... https://blog.cerowrt.org/post/trouble_in_paradise/
Comment linking /post/trouble_in_paradise/
on “Google Fiber is coming to Las Vegas”Submitted The new features and flaws of speedtest.net, ookla and Cloudflare as a story · 2 points
HN discussionAgreed. I fully expect to see the routers we used in the cerowrt project from 2008 still operational for 10-20 more years. Thereś one out there with 4+ years of uptime that I know of. https://blog.cerowrt.org/post/an_upgrade_in_place/
Comment linking /post/an_upgrade_in_place/
on “Ask HN: I’m an FCC Commissioner proposing regulation of IoT security updates”Submitted Net Neutrality advocates: Care to try some technical solutions instead? as a story · 2 points
HN discussionVint Cerf and I shot that proposed anti-dd-wrt regulation down thoroughly: filing here: http://www.taht.net/~d/fcc_saner_software_practices.pdf Substitute IoT for router in everything we wrote there on page 12-13 and that seems to be a starting point everyone around here has come to think is necessary. I would prefer not to summarize such a large filing here. Also Dan Geer wrote extensively on these topics at the ti…
Comment linking /post/an_upgrade_in_place/
on “Ask HN: I’m an FCC Commissioner proposing regulation of IoT security updates”Submitted I've never really recovered from the loss of the lab as a story · 2 points
HN discussionyes, had we found a way to support windows, we could have (and could still do) better. Regrettably we never did find a way - or funding - to drive tests through windows (wsl works). I still (as do many other folk in the Bufferbloat world) rely on flent to drive all kinds of tests. nothing compares to flent's ability to compare multiple network tests in so many ways. https://blog.cerowrt.org/post/flaws_in_flent/
Comment linking /post/flaws_in_flent/
on “Flent: The FLExible Network Tester”Submitted Solving the crypto-fq bug in ath9k as a story · 2 points
HN discussionone of my sadnesses is so few tests, except those designed by the bufferbloat project, test up + down + latency at the same time. I like this new one: https://github.com/Zoxc/crusader/releases/tag/v0.0.10-testin... . My favorite remains the rrul test out of the flent.org suite. Most web speed tests have nearly no predictive power for testing videoconferencing quality, although I am delighted speed test.net cloudflar…
Comment linking /post/speedtests/
on “Starlink cuts P99 Latency by 60% [pdf]”Submitted Dave Taht´s 2024 predictions for the Tech Industry as a story · 1 points
HN discussionI have tried to produce bufferbloat-related tools that measure things far more accurately and in more detail. https://blog.cerowrt.org/post/flaws_in_flent/
Comment linking /post/flaws_in_flent/
on “Speed Test”Submitted Drops at Juniper – exploring VOQ vs. SQM technology as a story · 1 points
HN discussion
