-
Notifications
You must be signed in to change notification settings - Fork 17
avoid headless #291
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.
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
base: main
Are you sure you want to change the base?
avoid headless #291
Conversation
Signed-off-by: Andrei Kvapil <[email protected]>
WalkthroughThe etcdcluster manifest was updated to simplify the DataStore endpoints from multiple pod-specific DNS entries to a single service DNS entry. Additionally, the DNS names in the etcd-server and etcd-peer Certificate specifications were expanded to include three more service-related DNS names. Changes
Poem
📜 Recent review detailsConfiguration used: CodeRabbit UI 📒 Files selected for processing (1)
⏰ Context from checks skipped due to timeout of 90000ms (7)
🔇 Additional comments (3)
|
…1128) ref to #1127, clastix/kamaji#856 and aenix-io/etcd-operator#291 <!-- This is an auto-generated comment: release notes by coderabbit.ai --> ## Summary by CodeRabbit * **New Features** * Updated etcd chart to version 2.9.0. * **Improvements** * Simplified etcd endpoint configuration to use a single static endpoint. * Expanded TLS certificate DNS names to include additional service addresses. * Streamlined resource configuration for etcd deployment. * **Chores** * Updated version mapping for etcd package. <!-- end of auto-generated comment: release notes by coderabbit.ai -->
This change references to upstream issue clastix/kamaji#856
It's better to use ordinary service instead accessing etcd via multiple endpoints from kubernetes-api due to DNS resloving issue, which might happen when one replica have no IP address assigned.