Replace DNS suffix when snapshot is restored in different cluster

[Copilot]

When snapshots are restored across clusters with different DNS suffixes, configuration files persist the old DNS suffix, causing resolution failures.

Changes

Enhanced fix_namespace_in_config_files in all entrypoint scripts to automatically replace DNS suffixes:

• node-entrypoint.sh: Handles node.conf
• sentinel-entrypoint.sh: Handles sentinel.conf
• cluster-entrypoint.sh: Handles node.conf and nodes.conf

Implementation

Regex pattern matches hostnames with multi-segment DNS suffixes and replaces the suffix while preserving the hostname:

# Pattern: ([hostname with ≥1 letter])\.(domain.segments)
sed -i -E "s/([a-zA-Z0-9_-]*[a-zA-Z][a-zA-Z0-9_-]*)\.(([a-zA-Z0-9-]+\.)+[a-zA-Z0-9-]+)/\1.${escaped_dns_suffix}/g"

Example transformation:

node-1.old-cluster.svc.cluster.local → node-1.new-cluster.svc.cluster.local

Key properties:

• Excludes IP addresses (hostname must contain ≥1 letter)
• RFC 1035 compliant (no underscores in domain segments, allowed in hostnames)
• Escapes sed metacharacters (&, \, /)
• Idempotent (safe on already-correct suffixes)

Triggered when LOCAL_DNS_SUFFIX environment variable is set, runs before server startup.

Original prompt

---

This section details on the original issue you should resolve

<issue_title>replace DNS suffix when snapshot is restored in different cluster</issue_title>
<issue_description></issue_description>

Comments on the Issue (you are @copilot in this section)

• Fixes replace DNS suffix when snapshot is restored in different cluster #550

---

✨ Let Copilot coding agent set things up for you — coding agent works faster and does higher quality work when set up for your repo.