i/Aether
1
0
Fork 0
mirror of https://github.com/fawney19/Aether.git synced 2026-10-10 03:09:50 +08:00
Code Issues Packages Projects Releases Wiki Activity

perf(gateway): scale request hot paths for 20k streams

Browse Source 
Shard and singleflight hot-path caches, batch and prioritize candidate and usage lifecycle persistence, and extend database and pressure-test instrumentation for 20k concurrent streams.
This commit is contained in:
elky
2026-07-22 02:11:08 +08:00
parent 7756c0913f
commit fc92c4f431
124 changed files with 36325 additions and 3217 deletions
Download Patch File Download Diff File Expand all files Collapse all files
apps/aether-gateway/src/tests/control/admin/pool.rs
+3
View File
@@ -3566,8 +3566,10 @@ async fn gateway_batch_updates_shared_pool_key_configuration() {
first_key.name = "alpha".to_string();
first_key.auto_fetch_models = true;
first_key.allowed_models = Some(json!(["legacy-model"]));
first_key.learned_rpm_limit = Some(18);
let mut second_key = sample_key("key-openai-b", "provider-openai", "openai:chat", "sk-b");
second_key.name = "beta".to_string();
second_key.learned_rpm_limit = Some(24);
let provider_catalog_repository = Arc::new(InMemoryProviderCatalogReadRepository::seed(
vec![provider],
Vec::new(),
@@ -3619,6 +3621,7 @@ async fn gateway_batch_updates_shared_pool_key_configuration() {
assert_eq!(key.api_formats, Some(json!(["openai:responses"])));
assert_eq!(key.internal_priority, 7);
assert_eq!(key.rpm_limit, None);
assert_eq!(key.learned_rpm_limit, None);
assert!(!key.auto_fetch_models);
assert_eq!(
key.allowed_models,