| Commit message (Collapse) | Author | Age | |
|---|---|---|---|
| * | Properly handle large messagesHEADdev | Robby Zambito | 2026-01-12 |
| | | | | | add max bytes setting | ||
| * | max buffer size way too small | Robby Zambito | 2026-01-12 |
| | | |||
| * | Add a warning log when producers are stalled | Robby Zambito | 2026-01-12 |
| | | |||
| * | Significant speed improvement | Robby Zambito | 2026-01-12 |
| | | |||
| * | Use appendAssumeCapacity instead of appendBounded catch unreachable | Robby Zambito | 2026-01-11 |
| | | | | | Basically the same thing. | ||
| * | Use cache line size for the cpu | Robby Zambito | 2026-01-10 |
| | | |||
| * | Cache align hot buffers | Robby Zambito | 2026-01-10 |
| | | |||
| * | Use much higher buffer sizes | Robby Zambito | 2026-01-10 |
| | | |||
| * | Sleep to go faster | Robby Zambito | 2026-01-10 |
| | | | | | | | | | | | The problem was I was basically flushing twice for every message when doing request reply. This gives the sender the opportunity to finish writing a full message to the queue, which we then check for before flushing. This makes request reply latency benchmarks go down from like 90ms to 200us. | ||
| * | Send should be uncancelable | Robby Zambito | 2026-01-10 |
| | | |||
| * | Use Subscription.send | Robby Zambito | 2026-01-10 |
| | | |||
| * | Properly handle disconnect | Robby Zambito | 2026-01-10 |
| | | |||
| * | switch to uuids for clients | Robby Zambito | 2026-01-10 |
| | | |||
| * | parsing cleanup | Robby Zambito | 2026-01-10 |
| | | |||
| * | More robust parsing and error propagation | Robby Zambito | 2026-01-08 |
| | | |||
| * | support hpub | Robby Zambito | 2026-01-08 |
| | | | | | | fixed issue where not all data was being sent request reply has a performance issue but technically works | ||
| * | WAY FASTER but doesn't send all? | Robby Zambito | 2026-01-07 |
| | | | | | Seems to not flush the last message | ||
| * | starting zero alloc parsing | Robby Zambito | 2026-01-07 |
| | | |||
| * | Cleanup Server.zig | Robby Zambito | 2026-01-06 |
| | | |||
| * | Major restructuring | Robby Zambito | 2026-01-06 |
| | | | | | This makes things much easier to use as a library | ||
| * | Better cancelation handling | Robby Zambito | 2026-01-06 |
| | | | | | | Based on this conversation with Andrew https://ziggit.dev/t/am-i-canceling-my-std-io-group-incorrectly/13836 | ||
| * | Restructuring | Robby Zambito | 2026-01-06 |
| Add a bunch of tests for the client | |||
