YGGverse/aquatic
1
0
Fork 0
mirror of https://github.com/YGGverse/aquatic.git synced 2026-03-31 17:55:36 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

README: remove ws benchmarks, since implementation changed

Browse source
This commit is contained in:
Joakim Frostegård 2021-12-16 17:03:30 +01:00 • committed by GitHub
parent 67c4c02bbd
commit 22f6d869d3
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
1 changed files with 0 additions and 29 deletions
Download patch file Download diff file Expand all files Collapse all files

29
README.md
View file

@ -172,35 +172,6 @@ clients, with some exceptions:
For TLS setup instructions, please see `aquatic_http` TLS section above.
#### Benchmarks
[wt-tracker]: https://github.com/Novage/wt-tracker
[bittorrent-tracker]: https://github.com/webtorrent/bittorrent-tracker
The following benchmark is not very realistic, as it simulates a small number
of clients, each sending a large number of requests. Nonetheless, I think that
it gives a useful indication of relative performance.
Server responses per second, best result in bold:
| workers | aquatic | [wt-tracker] | [bittorrent-tracker] |
|---------|------------|--------------|----------------------|
| 1 | n/a | __117k__ | 45k |
| 2 | __225k__ | n/a | n/a |
| 4 | __627k__ | n/a | n/a |
| 6 | __831k__* | n/a | n/a |
| 8 | __1209k__* | n/a | n/a |
| 10 | __1455k__* | n/a | n/a |
| 12 | __1650k__* | n/a | n/a |
| 14 | __1804k__* | n/a | n/a |
| 16 | __1789k__* | n/a | n/a |
\* Using a VPS with 32 vCPUs. The other measurements were made using a 16 vCPU VPS.
Please refer to `documents/aquatic-ws-load-test-2021-08-18.pdf` for more details.
__Note__: these benchmarks were made with the mio-based implementation.
## Load testing
There are load test binaries for all protocols. They use a CLI structure