GenarrativeAI/Genarrative
6
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat: add graceful api shutdown readiness

Browse Source
This commit is contained in:
kdletters
2026-06-05 11:43:56 +08:00
parent 9ab353926e
commit e5592304a5
19 changed files with 321 additions and 35 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
server-rs/crates/api-server/src/backpressure.rs
View File

@@ -102,7 +102,7 @@ fn reject_overloaded_request(request: &Request<Body>) -> Response {
}
fn should_bypass_backpressure(request: &Request<Body>) -> bool {
request.uri().path() == "/healthz"
matches!(request.uri().path(), "/healthz" | "/readyz")
}
fn classify_request_permit_pool(path: &str) -> HttpRequestPermitPoolKind {
@@ -200,6 +200,7 @@ mod tests {
.route("/held", get(held_request))
.route("/fast", get(fast_request))
.route("/healthz", get(fast_request))
.route("/readyz", get(fast_request))
.layer(middleware::from_fn_with_state(
backpressure_state,
limit_concurrent_requests,
@@ -297,6 +298,13 @@ mod tests {
.expect("healthz request should complete");
assert_eq!(health_response.status(), StatusCode::OK);
let ready_response = app
.clone()
.oneshot(test_request("/readyz"))
.await
.expect("readyz request should complete");
assert_eq!(ready_response.status(), StatusCode::OK);
gate.release.notify_one();
let completed_response = held_response
.await