TCP_BBR(4)

📦 version 15.1, in freebsd 14.5, freebsd 15.1, nixpkgs unstable

💅 TCP_BBR(4) — like, the whole manual, but make it make sense

okay bestie, so this is a Kernel Interfaces Manual page and it's about tcp_bbr, which literally stands for TCP Bottleneck Bandwidth and Round-Trip Time Algorithm. yes that's a mouthful, no we're not abbreviating it, it's iconic ✨

🌸 NAME 🌸

tcp_bbr — the TCP Bottleneck Bandwidth and Round-Trip Time Algorithm. that's the whole name, she's long, she's worth it 👑

🎀 SYNOPSIS 🎀

so there's two steps and you gotta do both, no skipping 🫶

Step one — load the driver as a module at boot time by putting this line in loader.conf(5):

tcp_bbr_load="YES"

Step two — to enable the TCP stack you must put this line in sysctl.conf(5):

net.inet.tcp.functions_default=bbr

like, "must" must. not optional. don't come back to me saying it doesn't work if you skipped one 😭

🦋 DESCRIPTION 🦋

so Bottleneck bandwidth and round-trip time (BBR) is a congestion control algorithm, and her whole thing is that she seeks high throughput with a small queue by probing BW and RTT. that's the vibe check she's passing 💅

she's a round-up redesign of congestion control — meaning she is not loss-based, not delay-based, not ECN-based, and not AIMD-based. not any of those. we're doing something new here, periodt.

the core design of BBR? it's all about creating a model graph of the network path by estimating the maximum BW and minimum RTT on each ACK. every single ACK, bestie. it's giving main character energy 🔥

🌈 MIB Variables 🌈

the algorithm exposes these scopes in the net.inet.tcp.bbr branch of the sysctl(3) MIB:

  • cwnd — Cwnd controls, for example "target cwnd rtt measurement" and "BBR initial window".
  • measure — Measurement controls.
  • pacing — Connection pacing controls.
  • policer — Policer controls, for example "false detection threshold" and "loss threshold".
  • probertt — Probe RTT controls.
  • startup — Startup controls.
  • states — State controls.
  • timeout — Time out controls.

and besides all the lil variables inside those scopes, these are also exposed in the net.inet.tcp.bbr branch 👇

  • clrlost — Clear lost counters.
  • software_pacing — Total number of software paced flows.
  • hdwr_pacing — Total number of hardware paced flows.
  • enob_no_hdwr_pacing — Total number of enobufs for non-hardware paced flows.
  • enob_hdwr_pacing — Total number of enobufs for hardware paced flows.
  • rtt_tlp_thresh — What divisor for TLP rtt/retran will be added (1=rtt, 2=1/2 rtt etc).
  • reorder_fade — Does reorder detection fade, if so how many ms (0 means never).
  • reorder_thresh — What factor for rack will be added when seeing reordering (shift right).
  • bb_verbose — Should BBR black box logging be verbose.
  • sblklimit — When do we start ignoring small sack blocks.
  • resend_use_tso — Can resends use TSO?
  • data_after_close — Do we hold off sending a RST until all pending data is ack'd.
  • kill_paceout — When we hit this many errors in a row, kill the session?
  • error_paceout — When we hit an error what is the min to pace out in usec's?
  • cheat_rxt — Do we burst 1ms between sends on retransmissions (like rack)?
  • minrto — Minimum RTO in ms.

💖 SEE ALSO 💖

go read these too, they're the friend group 🫶

and the reading list, because she's academic AND pretty 📚

  • Neal Cardwell, Yuchung Cheng, Stephen Gunn, Soheil Hassas Yeganeh, and Van Jacobson, “BBR: Congestion-Based Congestion Control”, ACM Queue, Vol. 14, September / October 2016.
  • Dominik Scholz, Benedikt Jaeger, Lukas Schwaighofer, Daniel Raumer, Fabien Geyer, and Georg Carle, “Towards a Deeper Understanding of TCP BBR Congestion Control”, IFIP Networking 2018, http://www.net.in.tum.de/fileadmin/bibtex/publications/papers/IFIP-Networking-2018-TCP-BBR.pdf, May 2018.

⭐ HISTORY ⭐

the tcp_bbr congestion control module first appeared in FreeBSD 13.0. slay, she's a 13.0 girlie 🎀

👑 AUTHORS 👑

the tcp_bbr congestion control module was written by Randall Stewart <rrs@FreeBSD.org> and sponsored by Netflix, Inc. — yes that Netflix, no cap 🔥

this manual page was written by Gordon Bergling <gbe@FreeBSD.org>. thank you Gordon, we love a documenter 💜

ngl bestie, if you're gonna mess with these sysctls on a live system, know what you're doing first — the page tells you what everything is, not what happens if you get it wrong 🙈

okay that's the whole page!! 🦋 she's from Debian, dated December 17, 2023, and she ate fr fr 💅✨

📦 where this page comes from