diff options
| author | eunhhu <[email protected]> | 2026-09-29 10:48:59 +0100 |
|---|---|---|
| committer | eunhhu <[email protected]> | 2026-09-29 10:48:59 +0100 |
| commit | 34fc79fe568784294a274851e3040c1171af1fe2 (patch) | |
| tree | b4860e9fd8a27f30e911f65d8ebd10d1158bb9c9 /research/experiments/013-parallel-syncs | |
| parent | 4bf5b1250b6f6dbf0f35525b61792de54624fab3 (diff) | |
| download | pure-34fc79fe568784294a274851e3040c1171af1fe2.tar.gz pure-34fc79fe568784294a274851e3040c1171af1fe2.zip | |
Let M6's path waver by 1 ms when flows share it, and count from 20 s of 60
With a fixed delay the drop-tail queue dropped one flow's packets eight
times as often as the other's by their phases alone (Floyd and Jacobson,
1992): Pure took 0.63-0.77 of the path from TCP and 0.69 from quinn,
0.47 from itself, and 0.49 under fq_codel. With 1 ms of jitter it takes
0.53 at an RTT of 20 ms.
Diffstat (limited to 'research/experiments/013-parallel-syncs')
0 files changed, 0 insertions, 0 deletions