diff --git a/docker-compose.yml b/docker-compose.yml index 96ec0b89a..671301fae 100644 --- a/docker-compose.yml +++ b/docker-compose.yml @@ -124,7 +124,13 @@ services: test: ["CMD", "python", "-c", "import urllib.request; urllib.request.urlopen('http://127.0.0.1:8000/healthz', timeout=2)"] interval: 5s timeout: 3s - retries: 20 + retries: 10 + # Warm-up window: failures inside start_period do not consume the retry + # budget, so a booting orchestrator that becomes healthy within 50s is + # never counted against retries. A dead service trips the gate at + # ~100s (start_period + 10 x 5s), matching the previous retries: 20 + # budget exactly; the win is boot tolerance, not faster dead detection. + start_period: 50s backend: build: