Skip to content

tcp_cubic: fix to achieve at least the same throughput as Reno

Mingrui Zhang netdev 4 versions – In review

Get series with b4
b4 am [email protected]

Versions newest first · linked by author and title

  1. v4 Latest3 patches 11 repliesIn review
  2. v33 patches 4 repliesSuperseded
  3. v23 patches 3 repliesSuperseded
Earlier versions · 1
VersionPostedPatchesRepliesStatus
v11 patch2 repliesSuperseded

Changes in v4 from the cover letter

replace min() with min_t()
separate declarations and code of tcp_cwnd_next_rtt
https://lore.kernel.org/netdev/[email protected]/

Patches in v4 No applies recorded yet

#Subject and filesSizeRepliesApplied
1/3tcp_cubic: fix to run bictcp_update() at least once per RTTnet/ipv4/tcp_cubic.c+5 -17 replies
2/3tcp_cubic: fix to match Reno additive incrementnet/ipv4/tcp_cubic.c+6 -14 replies
3/3tcp_cubic: fix to use emulated Reno cwnd one RTT in the futurenet/ipv4/tcp_cubic.c+6 -30 replies

Reviews trailers per patch

1 of 3 patches has a Reviewed-by or Acked-by.

PatchSoheil Hassas Yeganeh
1/3
2/3A-b
3/3

Trailers given in replies are filled; those carried in the patches from earlier versions are outlined with dashes.

Read the v4 thread

Cover letter [PATCH net v4 0/3] tcp_cubic: fix to achieve at least the same throughput as Reno

This series patches fixes some CUBIC bugs so that "CUBIC achieves at least the same throughput as Reno in small-BDP networks"
[RFC 9438: https://www.rfc-editor.org/rfc/rfc9438.html]

It consists of three bug fixes, all changing function bictcp_update() of tcp_cubic.c, which controls how fast CUBIC increases its congestion window size snd_cwnd.

(1) tcp_cubic: fix to run bictcp_update() at least once per RTT
(2) tcp_cubic: fix to match Reno additive increment
(3) tcp_cubic: fix to use emulated Reno cwnd one RTT in the future

Experiments:

Below are Mininet experiments to demonstrate the performance difference between the original CUBIC and patched CUBIC.

Network: link capacity = 100Mbps, RTT = 4ms

TCP flows: one RENO and one CUBIC. initial cwnd = 10 packets. The first data packet of each flow is lost

snd_cwnd of RENO and original CUBIC flows
https://github.com/zmrui/tcp_cubic_fix/blob/main/renocubic_fixb0.jpg

snd_cwnd of RENO and patched CUBIC (with bug fixes 1, 2, and 3) flows.
https://github.com/zmrui/tcp_cubic_fix/blob/main/renocubic_fixb1b2b3.jpg

The result of patched CUBIC with different combinations of bug fixes 1, 2, and 3 can be found at the following link, where you can also find more experiment results.

https://github.com/zmrui/tcp_cubic_fix

Thanks
Mingrui, and Lisong

Changes:
v3->v4:
replace min() with min_t()
separate declarations and code of tcp_cwnd_next_rtt
https://lore.kernel.org/netdev/[email protected]/
v2->v3:
Correct the "Fixes:" footer content
https://lore.kernel.org/netdev/[email protected]/
v1->v2:
Separate patches
Add new cwnd_prior field to hold cwnd before a loss event
https://lore.kernel.org/netdev/[email protected]/

Mingrui Zhang (3):
tcp_cubic: fix to run bictcp_update() at least once per RTT
tcp_cubic: fix to match Reno additive increment
tcp_cubic: fix to use emulated Reno cwnd one RTT in the future

 net/ipv4/tcp_cubic.c | 22 +++++++++++++++++-----
 1 file changed, 17 insertions(+), 5 deletions(-)
Signature · 1 line
2.34.1