summaryrefslogtreecommitdiff
path: root/src/Server.zig
Commit message (Collapse)AuthorAge
* Use cache line size for the cpuRobby Zambito2026-01-10
|
* Cache align hot buffersRobby Zambito2026-01-10
|
* Use much higher buffer sizesRobby Zambito2026-01-10
|
* Sleep to go fasterRobby Zambito2026-01-10
| | | | | | | | | | 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 uncancelableRobby Zambito2026-01-10
|
* Use Subscription.sendRobby Zambito2026-01-10
|
* Properly handle disconnectRobby Zambito2026-01-10
|
* switch to uuids for clientsRobby Zambito2026-01-10
|
* parsing cleanupRobby Zambito2026-01-10
|
* More robust parsing and error propagationRobby Zambito2026-01-08
|
* support hpubRobby Zambito2026-01-08
| | | | | 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 Zambito2026-01-07
| | | | Seems to not flush the last message
* starting zero alloc parsingRobby Zambito2026-01-07
|
* Cleanup Server.zigRobby Zambito2026-01-06
|
* Major restructuringRobby Zambito2026-01-06
| | | | This makes things much easier to use as a library
* Better cancelation handlingRobby Zambito2026-01-06
| | | | | Based on this conversation with Andrew https://ziggit.dev/t/am-i-canceling-my-std-io-group-incorrectly/13836
* RestructuringRobby Zambito2026-01-06
Add a bunch of tests for the client
generated by cgit (git 2.34.1) at 2026-02-02 14:01:34 +0000