Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

performance: user reports of different performance from ndt5 and ndt7 #326

Open
stephen-soltesz opened this issue Dec 7, 2020 · 3 comments

Comments

@stephen-soltesz
Copy link
Contributor

We've received several user reports of different performance from ndt5 vs ndt7 that could be a sign of something more widespread.

Case 1:

  • User reported leasing a symmetric 100Mbps connection. Typical traffic performed poorly, ~6Mbps down, but 90Mbps up still. Confirmed this using speedtest.net. However ndt7 from Google speed test onebox reported 60-90Mbps down. Similarly from the Nest Wifi via Google Home, also reported 90Mbps down. However, speed.measurementlab.net reported slow performance, ~6Mbps.
  • I confirmed with the users that ndt7 was actually downloading the data using the websocket messages from ndt server, i.e. TCPInfo.BytesAcked. It was not a client reporting bug.

Case 2:

  • M-Lab support user reported a 12x difference in the download speed from Google onebox (80-150Mbps) vs speed.measurementlab.net (6-12Mbps).

Cause is unidentified.

@bassosimone
Copy link
Contributor

I think this could be explained by BBR vs. Cubic in both cases (but @mattmathis surely knows better).

@laiyi-ohlsen
Copy link

Useful to include MinRTT if possible

@critzo
Copy link

critzo commented Jan 19, 2021

Related @support ticket:

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
None yet
Development

No branches or pull requests

4 participants