80b8ffdb4b
Use newer rustls-pki-types PEM parser API
2025-09-02 17:46:40 +00:00
f5632ce2ee
perf: move client and server on one binary
2025-08-26 05:36:31 +00:00
85dde101bd
perf: adopt more convential crate layout
2021-03-04 12:36:49 -08:00
da1014c913
Allow to set send and receive buffer sizes in perf application
...
Also default to 2MB, which provides reasonable baseline performance.
2021-03-04 11:01:42 +01:00
f38a877b76
Print perf server errors with context
...
This avoids losing error context
2021-03-04 11:01:42 +01:00
516dcd8885
Use debug instead of trace messages in the perf server
...
This provides basic output without seeing all the quic packet info in between.
2021-03-04 11:01:42 +01:00
312c0f041c
Perf: Use owned buffers
...
Use zero-copy APIs when sending data in perf application.
Performance difference:
1. First line is before
2. Second line is after (but with only the download write change)
```
│ Duration │ FBL | Upload Throughput | Download Throughput
──────┼───────────┼───────────┼───────────────────┼────────────────────
AVG │ 5.00ms │ 1.00ms │ 332.82 MiB/s │ 334.20 MiB/s
AVG │ 5.00ms │ 0.00ns │ 332.64 MiB/s │ 335.96 MiB/s
```
=> Makes less than 1%. Still neat to have
2021-03-02 09:13:00 +01:00
3de2727b94
Perf: Prefer more efficient cipher suites
...
Prefer AES128 in order to maximize throughput
2021-03-02 07:01:16 +01:00
82a065ac3e
Make perf up and download more efficient
...
Pass a bigger buffer to write calls to minimize the amount of write calls.
2021-03-02 07:01:16 +01:00
12039602ae
perf: use tokio::try_join instead of select
...
We want all subtasks to complete, and not only a single one.
2021-03-02 07:01:16 +01:00
a9aaf40943
Implement perf protocol for standardized benchmarking
2021-02-28 22:31:43 +01:00
Dirkjan Ochtman