Skip to content

Gateway: async healthcheck handler and explicit readiness probe timeout #865

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
lorenzo-norcini-scale wants to merge 1 commit into from
Closed

Gateway: async healthcheck handler and explicit readiness probe timeout #865

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions charts/model-engine/templates/gateway_deployment.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -60,6 +60,7 @@ spec:
path: /readyz
port: 5000
periodSeconds: 2
timeoutSeconds: {{ ((.Values.gateway).readinessProbeTimeoutSeconds | default 5) }}
failureThreshold: 30
command:
- dumb-init
Expand Down
6 changes: 6 additions & 0 deletions charts/model-engine/values.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -33,6 +33,12 @@ celery_broker_type_redis: null
# drop:
# - ALL

# gateway [optional] tuning for the gateway deployment.
gateway:
# readinessProbeTimeoutSeconds sets the /readyz probe timeout. The k8s default of 1s
# ejects saturated-but-healthy pods and concentrates load on the survivors.
readinessProbeTimeoutSeconds: 5

redis:
auth:
authSecretName: ""
Expand Down
9 changes: 7 additions & 2 deletions model-engine/model_engine_server/api/app.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -313,8 +313,13 @@ def load_redis():
get_or_create_aioredis_pool()


def healthcheck() -> Response:
"""Returns 200 if the app is healthy."""
async def healthcheck() -> Response:
"""Returns 200 if the app is healthy.

Must be async: a sync handler runs in the shared threadpool, so under load the
probe queues behind blocked requests and misses its timeout, ejecting pods that
are saturated but healthy.
"""
return Response(status_code=200)


Expand Down