mirror of
https://github.com/BerriAI/litellm.git
synced 2026-09-15 23:31:29 +00:00
33ec56ed75
The sequential version sent one request at a time, so a Redis outage never reached the concurrency where the failed-tracking alert body actually grows. This drives the proxy with locust against one model group of three mock deployments, two failing at order 1 and one serving at order 2, so every request spends its retries on the failing pair and lands on the serving deployment through the order-based fallback. Two phases, a healthy baseline and a CLIENT PAUSE WRITE window, and every request must succeed in both. Latency, RSS and CPU are reported as p50/p90/p99 per phase rather than asserted on: RSS and CPU come from psutil on the proxy's process tree, since a multi-worker proxy serves /metrics from the prometheus multiprocess collector and that drops the process collector's series. Thresholds stay open until weekly runs give real baselines. Co-Authored-By: Claude Code <noreply@anthropic.com> |
||
|---|---|---|
| .. | ||
| complexity_router_client.py | ||
| conftest.py | ||
| reliability_support.py | ||
| test_auto_router_regressions_e2e.py | ||
| test_complexity_router_e2e.py | ||
| test_reliability_cache_e2e.py | ||
| test_reliability_fallbacks_e2e.py | ||
| test_reliability_retries_e2e.py | ||
| test_reliability_timeouts_e2e.py | ||