Skip to content

fix: improve packet scheduling for not-validated paths#444

Draft
flub wants to merge 22 commits intomainfrom
flub/packet-scheduling-1
Draft

fix: improve packet scheduling for not-validated paths#444
flub wants to merge 22 commits intomainfrom
flub/packet-scheduling-1

Conversation

@flub
Copy link
Collaborator

@flub flub commented Feb 20, 2026

Description

wip

Breaking Changes

Notes & open questions

it's the weekend, this is useful in my head

so let's check in totally broken code.

so let's check in totally broken code.
@flub flub changed the title --- fix: improve packet scheduling for not-validated paths Feb 20, 2026
@flub flub marked this pull request as draft February 20, 2026 18:14
@github-actions
Copy link

github-actions bot commented Feb 20, 2026

Performance Comparison Report

98efdff3f249e69dee299311b4b3b82fb0adeee7 - artifacts

No results available

---
5de87e12310b73113f22a08f51f8e173c65aaa10 - artifacts

No results available

---
ff11b1c69b15c27f90963169076e9d868dbd2b9d - artifacts

No results available

---
cec40b266637af7778ae5095e77591f986d6980e - artifacts

No results available

---
cb9e52aa685a7606f179a832f5f143274b59fc73 - artifacts

No results available

---
e9832764982048515e9d70cde799c2ff72068814 - artifacts

No results available

---
580e0445f5cd1b35963c50c49df51322c9977498 - artifacts

Raw Benchmarks (localhost)

Scenario noq upstream Delta CPU (avg/max)
large-single N/A 7935.4 Mbps N/A N/A
medium-concurrent N/A 7741.4 Mbps N/A N/A
medium-single N/A 4749.1 Mbps N/A N/A
small-concurrent N/A 5259.7 Mbps N/A N/A
small-single N/A 4709.0 Mbps N/A N/A

Netsim Benchmarks (network simulation)

Condition noq upstream Delta
ideal N/A 4008.8 Mbps N/A
lan N/A 810.4 Mbps N/A
lossy N/A 55.9 Mbps N/A
wan N/A 83.8 Mbps N/A
---
b67d78083f447c69f2dc68dcc918955984ec5b2f - artifacts

No results available

---
c3eed892cf6ab907aeb98ecea15d44d7548c6654 - artifacts

Raw Benchmarks (localhost)

Scenario noq upstream Delta CPU (avg/max)
large-single N/A 7871.6 Mbps N/A N/A
medium-concurrent N/A 7738.9 Mbps N/A N/A
medium-single N/A 4612.9 Mbps N/A N/A
small-concurrent N/A 5073.2 Mbps N/A N/A
small-single N/A 4709.9 Mbps N/A N/A

Netsim Benchmarks (network simulation)

Condition noq upstream Delta
ideal 748.4 Mbps 3980.5 Mbps -81.2%
lan 572.7 Mbps 800.6 Mbps -28.5%
lossy 69.9 Mbps 69.9 Mbps ~0%
wan 83.8 Mbps 83.8 Mbps ~0%

Summary

noq is 70.1% slower on average

---
453fa89b88ef3d18fb15da390fd464e916bc5d1f - artifacts

Raw Benchmarks (localhost)

Scenario noq upstream Delta CPU (avg/max)
large-single N/A 7916.7 Mbps N/A N/A
medium-concurrent N/A 7605.0 Mbps N/A N/A
medium-single N/A 4749.1 Mbps N/A N/A
small-concurrent N/A 5384.7 Mbps N/A N/A
small-single N/A 4844.6 Mbps N/A N/A

Netsim Benchmarks (network simulation)

Condition noq upstream Delta
ideal 739.2 Mbps 3951.3 Mbps -81.3%
lan 572.7 Mbps 810.3 Mbps -29.3%
lossy 55.9 Mbps 55.9 Mbps ~0%
wan 83.8 Mbps 83.8 Mbps ~0%

Summary

noq is 70.4% slower on average

@n0bot n0bot bot added this to iroh Feb 20, 2026
@github-project-automation github-project-automation bot moved this to 🚑 Needs Triage in iroh Feb 20, 2026
@matheus23
Copy link
Member

I know this is WIP code, but I want to call out that this contains partly some really useful refactors (moving PollPathTransmitStatus etc. around, matching on rhs instead of using rhs.*), and partly some other unrelated changes (introducing a PathSchedulingInfo struct).

Stacking these two in separate stacked PRs might make it easier to review.

I know this is draft - so feel free to ignore me :)

@flub flub linked an issue Feb 23, 2026 that may be closed by this pull request
@dignifiedquire dignifiedquire moved this from 🚑 Needs Triage to 🏗 In progress in iroh Feb 23, 2026
@github-actions
Copy link

github-actions bot commented Mar 2, 2026

Documentation for this PR has been generated and is available at: https://n0-computer.github.io/noq/pr/444/docs/noq/

Last updated: 2026-03-09T16:25:18Z

flub added 4 commits March 9, 2026 12:33
Slightly sad to have to make an explicit exception for this, at least
currently.
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

Status: 🏗 In progress

Development

Successfully merging this pull request may close these issues.

Improve packet scheduling

2 participants