Triage and recover load testing

Map failure classes for POST /v1/chat/completions (stream): retryable vs fatal vs needs-human. Retries need budgets, jitter, and idempotency rules aligned to abort if error_rate > 1% or p95_ttft > 1.5s; test cost ≤ $50. The chapter’s signature failure — load generator retries hide server shedding — false green — must take a deliberate branch, not a generic catch-all.

Implement the degrade/rollback/refuse behavior capacity planner before Black Friday traffic 3× baseline needs when LOAD-FALSE-GREEN-33 repeats. Prefer scoped controls (one flag, one weight, one tenant, one secret version) over fleet-wide restarts. Preserve evidence; do not delete logs to “clean the demo.”

After containment, check saturation_rps, p95_ttft_ms, test_usd moves in the safe direction and watch for retry amplification. Write the stop condition that ends the incident response for this lab.

Chaos note: inject only one fault class at a time and restore fixtures after. Watch for dual failures — dependency down and retry amplifier — which is how load generator retries hide server shedding — false green becomes an outage. Customer communication templates (even if only for the drill) beat silence. If you queue deferred work, define poison-message handling. Budget documents should state the maximum extra spend allowed during retries. Close the loop by linking the containment action to a dashboard panel for saturation_rps, p95_ttft_ms, test_usd.

Draw a state diagram for degrade modes and put it in the repo as ASCII if needed. Cap concurrent retries across the process, not only per request. Ensure cancellation propagates to downstream HTTP clients. When failing closed, choose a user-visible message that does not leak internals. Practice the single command that flips the kill switch or weight to zero. After recovery, drain or inspect deferred work before declaring green. In this chapter the product is k6 streaming load test for chat completion gateway, the human stakeholder is capacity planner before Black Friday traffic 3× baseline, and the incident id you design against is LOAD-FALSE-GREEN-33. Re-state the oracle in your notes — find saturation knee near 180 RPS; beyond that queue depth explodes — and keep the invariant visible: abort if error_rate > 1% or p95_ttft > 1.5s; test cost ≤ $50. Track saturation_rps, p95_ttft_ms, test_usd as the scoreboard. Surface under change control: POST /v1/chat/completions (stream). If you only have forty minutes, finish the fixture for load generator retries hide server shedding — false green before polishing UI. Promotion language stays ternary: promote, hold, or roll back based on evidence, not hope.