agent-substrate / agent-substrate/substrate

[benchmarking] Expose host kernel PSI metrics and relabel root cgroup in cAdvisor

Đang mở
#1,588 0 bình luận 0 reaction 0 người được giao Xem trên GitHub
area/benchmarking area/observability kind/feature
Ngôn ngữ chính
Go
Star
1.8k
Fork
316
Merge trung bình
2 ngày 43 phút
Pull request đã merge (30 ngày)
287

Mô tả

### Background & Problem
When benchmarking Agent Substrate under realistic agent workloads (running test suites, compilation, and git operations across concurrent actor sandboxes), diagnosing whether tail latency spikes and cold-start regressions stem from CPU throttling, memory thrashing, or disk I/O contention requires Linux kernel Pressure Stall Information (PSI).

Currently, cAdvisor in `benchmarking/monitoring.yaml` drops PSI metrics and leaves the root cgroup `id="/"` unlabeled, making it difficult to isolate host-level resource starvation from actor container pressure.

### Proposed Changes
1. Relabel the root cgroup `id="/"` to `container="node"` in the cAdvisor scrape job in `benchmarking/monitoring.yaml`.
2. Expand the metric allowlist to capture `container_pressure_{cpu,memory,io}_waiting_seconds_total`, along with network throughput and filesystem usage.

### References
- [Substrate Benchmark Telemetry & Metrics Enhancement](https://docs.google.com/document/d/1f9b1mTyxICeLZPojrxCujZ16Elh4IFo3_WmBeNCvk1c/edit?pli=1&tab=t.0)
- [Agent Substrate: Actor Density Benchmark Specs](https://docs.google.com/document/d/1sv5aBXvGOQ69iaqFxdPZ-d6tNbh5AMuwKODDyYjzYQw/edit?tab=t.0)

cc @maxsmythe @roycaihw - happy to submit a PR for this!

Hướng dẫn đóng góp

Mở hướng dẫn đóng góp

Đánh giá

Issue này chưa được đánh giá.

Nhận issue mới trong hộp thư của bạn

Bản tóm tắt ngắn những issue GitHub phù hợp với người mới.