scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-09-15 23:31:29 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 213

test(e2e): tighten chaos latency ceilings to 1s/2s/3s

Browse source 
Local runs measured p50 0.19s, p90 0.23s, p99 0.69s, so 2s/3s/5s left several
times that as slack. 1s/2s/3s keeps a comfortable margin while catching a
smaller regression than the looser ceilings would have.

Co-Authored-By: Claude Code <noreply@anthropic.com>
This commit is contained in:
Kerry Lu 2026-09-11 13:45:11 -07:00
parent e81a788776
commit a1f9f4cbe8
1 changed files with 5 additions and 5 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

10
tests/e2e/load/test_redis_chaos_e2e.py
View file

@ -84,11 +84,11 @@ CHAOS_CPU_PER_REQUEST_RATIO_CEILING: Final = 2.0
# the breaker opens, a request skips Redis rather than waiting on its socket timeout, so the chaos
# phase can come in faster than baseline (local runs measured p90 at 0.61x) and a ratio passes on a
# phase that was never slow. What a user actually cares about is the wall-clock number, which these
# hold directly. Calibrated from local runs whose worst chaos phase was p50 0.66s, p90 0.74s, p99
# 1.20s and 3.4 KB of log per request, then left roughly 3x loose for a shared CI runner.
CHAOS_P50_LATENCY_CEILING_SECONDS: Final = 2.0
CHAOS_P90_LATENCY_CEILING_SECONDS: Final = 3.0
CHAOS_P99_LATENCY_CEILING_SECONDS: Final = 5.0
# hold directly. Calibrated from local runs whose worst chaos phase was p50 0.19s, p90 0.23s, p99
# 0.69s and 3.5 KB of log per request, with several times that left as slack for a shared CI runner.
CHAOS_P50_LATENCY_CEILING_SECONDS: Final = 1.0
CHAOS_P90_LATENCY_CEILING_SECONDS: Final = 2.0
CHAOS_P99_LATENCY_CEILING_SECONDS: Final = 3.0
CHAOS_LOG_BYTES_PER_REQUEST_CEILING: Final = 12_000.0
DRAIN_TIMEOUT_SECONDS: Final = 30.0