Skip to content

Commit 48471ad

Browse files
stuggiclaude
andcommitted
[docs] blue/green: stop all OpenStack services on A before the backup
After the drain, all OpenStack services on A are scaled to zero while A's infrastructure (Galera, RabbitMQ, memcached, OVN, dnsmasq) keeps running. The backup becomes a real freeze with a consistent cut across all Galera clusters, and only B can act on shared backends afterwards. This removes the duplicate-actor risks from the residual risk list and shrinks B's fence list to the reactions to EDPM not being attached yet: OVN gateway, InstanceHA, octavia health-manager/housekeeping, aodh, heat-engine and watcher. EDPM stays attached to A's infrastructure until the switch, so north-south traffic through ctlplane gateways keeps working during the window. Rollback before the switch only restarts A's services. After the switch it follows the switch sequence with roles swapped. A's DBs are unchanged since the stop. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
1 parent 8ca880f commit 48471ad

1 file changed

Lines changed: 46 additions & 34 deletions

File tree

0 commit comments

Comments
 (0)