cortex

cortex copied to clipboard

Prometheus Configuration in Version 0.42

1

Hi, We have recently migrated from version 0.35 to 0.42 and have observed that the Prometheus config has changed. We are no longer getting metrics such as kube_pod_status_phase etc. Although...

17Ants

Custom predict path for Async API

1

Is there a way to change the "default" path "/" to add a prefix like "/predict" for AsyncAPI? ``` - name: text-generator kind: AsyncAPI pod: port: 8080 - http: paths:...

imshashank

Support API response caching

1

deliahu

Persist Prometheus metrics to S3 instead of a persistent volume

1

Thanos can be used for this

deliahu

checklist: - [x] run `make test` and `make lint` - [x] make sure the targeted metrics still make sense - [ ] verify the dashboards

RobertLucian

RealtimeAPI CRD

7

checklist: - [x] run `make test` and `make lint` - [x] test manually (i.e. build/push all images, restart operator, and re-deploy APIs)

miguelvr

Handle AWS termination notice for spot instances

1

#### Motivation Respond to spot instance terminations more gracefully. That is to prevent getting failed requests when the traffic is supposed to migrate from the terminating instance to another one...

deliahu

#### Description Report any error (as it can be seen in `cortex describe `) that might occur due to an API misconfiguration. The Sentry DSN has to be configured by...

RobertLucian

#### Description Helps reduce the scale-out time. #### Additional https://docs.aws.amazon.com/autoscaling/ec2/userguide/ec2-auto-scaling-warm-pools.html https://medium.com/keikoproj/rapid-auto-scaling-on-eks-part-2-d094b9b2cd62 ##### Notes On the pricing model: > You have the option of keeping instances in the warm pool in...

RobertLucian

#### Notes Must be done at the activator level.

RobertLucian