Skip to content

Fix cache-aware router should pick min load instead of min tenant size #14650

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
slin1237 merged 1 commit into from
Dec 8, 2025
Merged

Fix cache-aware router should pick min load instead of min tenant size #14650

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 4 additions & 1 deletion sgl-model-gateway/src/policies/cache_aware.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -309,7 +309,10 @@ impl LoadBalancingPolicy for CacheAwarePolicy {
matched_worker.to_string()
} else {
RouterMetrics::record_cache_miss();
tree.get_smallest_tenant()
let min_load_idx = *healthy_indices
.iter()
.min_by_key(|&&idx| workers[idx].load())?;
Comment on lines +312 to +314
Copy link
Contributor

@gemini-code-assist gemini-code-assist bot Dec 8, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

medium

This logic for finding the worker with the minimum load is also present earlier in this function (lines 261-264). For consistency and to use a more idiomatic approach, it would be better to use .copied() instead of dereferencing with *. This also makes the code identical to the existing implementation, reducing duplication.

Suggested change
let min_load_idx = *healthy_indices
.iter()
.min_by_key(|&&idx| workers[idx].load())?;
let min_load_idx = healthy_indices.iter().min_by_key(|&&idx| workers[idx].load()).copied()?;

workers[min_load_idx].url().to_string()
};

// Find the index of the selected worker
Expand Down
Loading